JPH05233161A - Method and device for data multiplex write - Google Patents

Abstract

PURPOSE:To suppress the deterioration of processing time when a storage device having plural disk devices writes data and to secure high input/output performance. CONSTITUTION:This device is composed of a disk device group where the disk device l16 storing data and the control part 17 are made into a pair, an input/output management part receiving instructions from a host device such as CPU 1 rearranging them in the order of priority and transmitting them to a low-order, a buffer which temporarily stores the instructions, a command processing management part 75 decoding the instructions sent from the input/ output management part 70 calculating the addresses of the instructions and sending them to a low-order management part, a data address management table 50 storing the data addresses, a blank area management table 55 storing the address where data is not stored, a disk device management part 85 sending the instruction sent from the command processing management part to the disk device group and monitoring a use situation and the presence or absence of the occurrence of a fault, a disk device management table 60 recording the result and a multiplex/fault management part 80 multiplexing data and executing restoration when the fault occurs.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a data read / write control method and apparatus in a secondary storage device used in a data processing device, and more particularly, to a plurality of secondary storage devices such as disk drives. The present invention relates to a method and apparatus for performing multiple write control of the same data on a predetermined number of storage units.

[0002]

2. Description of the Related Art Up to now, the performance improvement of a secondary storage device has been mainly directed to an increase in storage device capacity and an increase in data transfer rate. However, as the processing speed of the computer is improved, the improvement of the input / output throughput with respect to the secondary storage device is becoming an issue. The first solution is to write the same data to all n (n is an integer of 2 or more) disk drives, and when reading data, issue a data output command to all disk drives, A method of reading the data from a disk drive capable of processing the data output command has been proposed.

About this, Dina Bi of the University of Illinois
Tton et al .: Disk Shadowing (Dina Bitt
on, et al, “Disk Shadowing”, Proceedings of the
14th International Conference on Very Large Data B
ase, 1988, pp.331-338) and JP-A-1-17101.
It is disclosed in Japanese Patent Publication No. 5 (JP-A-1-17015).

As another method for improving the input / output throughput, there is known a technique in which a plurality of disk drives are independently driven and one data is divided and written into the plurality of disk drives. For example, RAID (Redundant Ar) announced by the University of California, Berkeley
rays of Inexpensive Disks) method.

Regarding this, a case of redundant array of inexpensive discs (David A. Patterson, et al, et al.
“A Case of Redundant Array of Inexpensive Disks
(RAID) ”, ACMSIGMOD Conference, 1988).

[0006] Here, a technique of high reliability using parity, ECC, etc. is shown for the problem of reliability deterioration due to data being divided and stored in a plurality of disk drives. That is, for each data, correction data is created using parity, ECC, and the like.
When a failure occurs in a certain disk drive, a technique for recovering the data in the failed disk drive from the correction data and the data remaining in the normal disk drive is disclosed. This technique is disclosed, for example, in Japanese Patent Laid-Open No. 2-236714 (JP-A-2-236714).

[0007]

In the former technique, which is represented by the paper "Disk Shadowing", the waiting state of input / output commands in each disk drive is considered when the same data is read / written to a plurality of disk drives. Not not. Therefore, when writing the same data to a plurality of disk drives, if the plurality of disk drives include at least one disk drive that already has a large number of input / output commands, the same data writing operation is performed as a whole. I'll be late.

Further, when the same data is read from a plurality of disk drives, a read command is issued to all the disk drives storing the data, so that there is little possibility of reading the data earliest. For a disk drive that already has a large number of input / output instructions, unnecessary input / output instructions will be added.

On the other hand, even in the latter technique represented by the paper "RAID", the waiting state of the input / output command in each disk drive is not taken into consideration at the time of data read / write operation for a plurality of disk drives. Also,
If a disk drive fails, special recovery data is needed to recover it.

It is a primary object of the present invention to provide a same data multiple write control method and device which improves the input / output throughput of a secondary storage device having a plurality of storage units.

It is another object of the present invention to provide a method and apparatus for controlling multiple writing of the same data in a secondary storage device that can automatically generate history data.

Another object of the present invention is to provide a multiple data read / write control method and device for the same data in a secondary storage device having a plurality of storage units, which has less influence on other input / output instructions. is there.

Still another object of the present invention is to control multiple reading / writing of the same data in a secondary storage device having a plurality of storage units so that data can be easily recovered when a failure occurs in the storage unit. A method and apparatus are provided.

Still another object of the present invention is to provide a method and apparatus for controlling multiple read / write of the same data, which is flexible in addition of an unused storage unit in a secondary storage unit having a plurality of storage units. To provide.

[0015]

According to a preferred embodiment of the present invention, the above object is to provide a secondary storage device having a plurality of storage units with the same storage unit having a low degree of waiting for input / output instruction processing. This is achieved by selecting data as a storage unit group to be multiple-written.

Further, according to a preferred embodiment of the present invention, the above-mentioned object is taken into consideration in a secondary storage device having a plurality of storage units, the data free capacity of each storage unit and the degree of waiting for processing of input / output instructions. Then, it is achieved by selecting a storage unit in which the same data is to be multiple-written.

[0017]

As shown in FIG. 15, the multiplexed storage device of the present invention stores one data in a plurality of storage units (disk device # 1,
# 3) If you want to process the output life to store it,
Since the data is called from the storage unit which has become the earliest available and the data #n is used, the output processing performance can be improved. In addition, the controller processes the plurality of input / output instructions, and if the storage unit that stores the input data cannot be used for processing another input / output instruction, another storage unit that can be used earliest ( Disk device # 2, #
Since the data #n is written in the empty area of 4), it is possible to improve the input processing performance. By associating the address specified by the input / output command with the number and address of the storage unit where the data is actually stored and managing them automatically in the data address management table,
The user can perform optimum input / output processing without worrying about the position of the data in the storage unit. In addition, when the failure recovery of the storage unit is performed, the data to be read is dispersed in each storage unit, and it is not necessary to concentrate and occupy only one storage unit. Also, since the writing is not concentrated on only one storage unit, it is possible to suppress the deterioration of the processing performance of the input / output request. Also, if you cannot read or write data due to memory failure,
To compensate for this by reading the other multiplexed data on the memory, and when all the multiplexed data becomes unusable, increase the reliability by substituting the stored history data. Can be done.

[0018]

Embodiments of the present invention will now be described in detail with reference to the drawings.

FIG. 1 shows the configuration of an embodiment of the secondary storage device according to the present invention. In this embodiment, a secondary storage device having magnetic disk drives as a plurality of storage units will be described as an example. In FIG. 1, the secondary storage device includes a control unit 2 that controls the entire plurality of storage units, magnetic disk drives 16-1 to 16-n, and a disk control device 15 that controls the magnetic disk drives 16-1 to 16-n.

In FIG. 1, reference numeral 1 is a CPU which is a higher-level device.
In response to the user's instruction, the CPU 1 issues a command to the secondary storage device 101 and receives the processing result. The control unit 2 manages input / output commands from the CPU 1, manages files (data) to be stored, and the like.
The command issued from the CPU 1 passes through the external interface path 3 and the interface port (hereinafter referred to as I
F prot). Although FIG. 1 shows the configuration of two systems, only the operation of one system will be described below to simplify the description. The other system also performs the same operation. The microprocessor (MP) 11-1 is
Check if there is a path that can be used in external interface path 3 and use external interface path 3
If there is, the MP 11-1 switches the channel path switch (hereinafter CPS) 5 to perform the command reception process.
If the command is not accepted, MP11-1
Sends an unacceptable response to the CPU 1.

The received command is sent to the channel port circuit (CHL prot) 6-1 and the channel protocol is converted into the protocol in the control unit 2. The converted command passes through the internal command path 10-1, to the command buffer (CBUF) 7-1, and the data passes through the internal data path 9-1 to the data buffer (DBU).
F) It is temporarily placed in 8-1 and waits for the next processing.

The management table (MT) 12 includes a data address management table 50 for managing addresses of data stored in each disk drive.
An empty area management table 55 for managing the empty area of each disk drive and a drive management table 60 for managing the status of each disk drive are placed.

The data that has been appropriately processed by the MP 11-1 is converted by the drive port 13-1 so as to match the protocol of the drive data path 19. The command is also sent to the drive processors 17-1 to 17-n through the drive command path 18. MP11
-1 checks whether there is an available path in the drive data path 19 according to the command. When there is a usable drive data path 19, the MP 11-1 switches the drive path switch (DPS) 14 to send commands and data to the drive processors 17-1 to 17-n.
If it cannot be accepted, the fact that it cannot be accepted is registered in the drive management table 60.

The arbitration processor 15-1 controls the internal command path 10. Each of the drive processors 17-1 to 17-n has a disk drive 16
-1 to 16-n are controlled to move the head, wait for rotation, detect a fault occurrence, report each disk drive 16-1 to 16
-N and data transfer of the control unit 2 are controlled. The numbers of the drive processors 17-1 to 17-n and the disk drives 16-1 to 16-n are generally arbitrary.

In this embodiment, the same data sent from the CPU 1 is stored in a plurality of disk drives by multiple writing.

In FIG. 2, MP11-1 or MP11-
2 shows the processing executed in 2 and the contents of the MT 12. As is apparent from FIG. 1, in this embodiment, MP11-1 and M
Although there are two systems, P11-2, only the ten systems will be described for convenience of explanation. The MP 11-1 includes an input / output management unit 70 that performs command and data queuing processing, a command processing management unit 75 that performs command address conversion, management of empty areas, etc., multiple data write / read, and failure recovery processing. A multiple write / read failure management unit 80 for carrying out and a disk drive management unit 85 for managing the usage and status of the disk drive are prepared. Further, a data address management table 50, a free area management table 55, and a drive management table 60 are prepared in the MT 12 as a place for storing information necessary for these processes. CBUF7-1 and DBUF8-1 are prepared as buffers used when executing the input / output management unit 70. In addition, the drive processors 17-1 to 17-1
The 7-n has a disk drive control unit 90 which performs command processing, seek, search, data reading, writing, etc. in the disk drives 16-1 to 16-n.

In FIG. 3, the data address management table 5 is shown.
The structure of 0 is shown.

As shown in FIG. 3, the data address management table 50 includes a plurality of areas described below. 100
-1 and 100-2 are areas in which a user number for identifying a user and an allocated storage capacity usable by the user are registered, and are defined for each user. In FIG. 3, the user number 1 is assigned a storage capacity of M1 bytes, and the user number 2 is assigned a storage capacity of M2 bytes.

105-1 and 105-2 are logical addresses designated by the CPU 1 as data storage locations,
This is an area for registering the number of history records (the number of data that the data has before the update). In the example of FIG. 3, the logical address 1 has a history retention number of 3, and the logical address 2 has a history retention number of 4.
have.

120-1, 120-2 and 120-3
Is an area for registering the history number indicating the order in which the data was updated and the data multiplicity (the number of disk drives storing the same data). In this embodiment, the newer the data, the smaller the history number. In FIG. 3, the multiplicity 3 is registered in the history number 1, the multiplicity 3 is registered in the history number 2, and the multiplicity 4 is registered in the history number 3.

130-1, 130-2 and 130-3
Is an area for registering a disk drive number for identifying a plurality of disk drives in which the data is stored, and a physical address and a data capacity of an area where the data is actually stored in the disk drive. In the example of FIG.
Of the triple-written data, one is stored at the physical address A1 of the disk drive # 1, and the other is
Stored at physical address A2 of disk drive # 2,
The remaining one is the physical address A of disk drive # 4.
It is stored in 3. Since the data is the same, the data capacities of the areas 130-1, 130-2, and 130-3 are equal and are D1 bytes.

A plurality of areas 105 are connected to the area 100, a plurality of areas 120 are connected to each area 105, and a plurality of areas 130 are further connected to the area 120. The entire data address management table 50 is a tree. It has a structure. In this embodiment, the entire data address management table 50 has a tree structure, but it is possible to have another list structure or table structure.

As described above, one piece of data is multiplexed, and as shown by the data address management table 50, the past history data is held. Therefore, the data capacity of each user can be calculated by taking the sum of the data capacity multiplied by the multiplicity and the number of history records.
For example, the number of data managed by the user number j is N, the data capacity of each data, the multiplicity, and the number of history records are C respectively.
If i, Mi, and Hi, the data capacity U of the user number j
Cj is represented by the following equation 1.

[0034]

[Equation 1] Further, assuming that the number of users is L, the data capacity UC used by all users is represented by the following expression 2.

[0035]

[Equation 2] Therefore, the minimum UC for the multiple storage units as a whole
Only data capacity is required.

In the case of the preferred embodiment, which enables improved performance and reliability in reading and writing data, it is necessary that all multiplexed data be written to different disk drives. Therefore, it is desired that the number of disk drives is larger than the multiplicity. However, if it is only necessary to improve the performance at the time of reading, writing can be performed at different positions in the same disk drive. In that case, the number of disk drives may be less than the multiplicity.

Next, referring to FIG. 4, the empty area management table 55
The structure of will be described.

In FIG. 4, 200-1 to 200-n are disk drive numbers, and each disk drive 16-
It is defined for each of 1 to 16 to n. 205-1 ~ 20
Reference numeral 5-7 is an area for registering a physical address indicating an empty area in which data of each disk drive 16-1 to 16-n is not stored and a data capacity that can be stored in the empty area. In FIG. 3, the disk drive number # 1 has an empty area 20.
5-1 and 205-2 exist, and the disk drive number #
3 have free areas 205-3 and 205-4, a free area 205-5 exists in the disk drive number # 4, and free areas 505-6 and 205 exist in the disk drive number #n.
-7 is present. It is indicated that the disk drive # 2 has no free area. Empty area management table 55
The whole has a list structure. In this embodiment, the entire empty area management table 55 has a list structure, but it is also possible to have a tree structure or a table structure. The capacity of the empty area of the plurality of storage units is equal to that of each disk drive 16-1
It can be calculated by adding up the data capacities of the areas 205 for each 16 to 16-n and taking the sum total for each disk drive. EC of the free space capacity of each disk drive
Assuming that k is the number of disk drives and D is the number of disk drives, the empty area capacity EC required for the entire plurality of storage units can be expressed by the following expression 3.

[0039]

[Equation 3] When the capacity of the data in the empty area is EC, the storage capacity AC required for the entire plurality of storage units is the sum of the data capacity UC and is expressed by the following equation 4.

[0040]

AC = EC + UC (Equation 4) The plurality of storage units in this embodiment improve input / output processing performance by writing input data to the empty area of the other disk drive that can be used earliest. For this reason,
In order to bring out the performance sufficiently, it is necessary to sufficiently secure the capacity ECk of the empty area of each disk drive. If this free space is insufficient or does not exist, the data will be written to the disk drive that has already received another I / O command, but even at this time, the I / O processing performance will be better than that of ordinary multiple storage units. It does not decrease. Further, when there is no empty area, it is possible to reduce a part or the multiplicity of the history data shown in FIG. 3 and turn the resulting area into an empty area.

In addition, in addition to this, a memory save area such as the data address management table 50, the empty area management table 55, and the empty area management table 60, and a confirmation area for the recovered data are required.

FIG. 5 shows a disk device management table 60.
The structure of is shown below.

In FIG. 5, the disk device management table 60 includes a disk drive number registration area 401 for identifying each disk drive 16-1 to 16-n, and a processing wait for each disk drive 16-1 to 16-n. An area 402 for registering the number of input / output instructions is included. In FIG. 5, the number of input / output requests is represented by a 3-digit binary number in the input / output command number registration area 402. If there is a disk drive that has become unusable due to a failure in the pending input / output instruction registration area 402, a flag indicating that the disk drive is unavailable can be set in the area 402 corresponding to the disk drive. In FIG. 5, the maximum value “111” represented by a 3-digit binary number is used as a flag indicating that the use is disabled. That is, the disk drive number # 5 is unusable in FIG. Also, FIG. 5 shows the disk drive number # 2.
There is no I / O command waiting for processing in the disk drives 16-2 to 16-n of #n, and six I / O commands are waiting for processing for the disk drive 16-1 of disk drive number # 1. It is shown in.
Also, disk drive 1 with disk drive number # 3
Reference numeral 6-3 indicates that it has three process waiting input / output instructions.

Next, referring to the flowchart of FIG. 6, the input / output management unit 70, the CBUF 7-1 (or 7-2), the DB
The processing procedure of the UF8-1 (or 8-2) will be described.

When the input / output management unit 70 starts the input / output processing, it first checks the states of the input / output instructions and data held in the CBUF7-1 and DBUF8-1 (step 50).
5). Here, the queues in the CBUF 7-1 and DBUF 8-1 are counted and it is confirmed whether or not the threshold value set in advance is exceeded. CBUF7-1, DBUF8-
If the number of queues in 1 is less than or equal to the threshold value, it is checked in the next step whether or not there is an input / output instruction sent from the CPU 1 (step 510). If a new input / output command comes from the CPU 1, the input of the input / output command is accepted (step 515). Next, the input / output instruction accepted in step 515 is stored in the queues in CBUF7-1 and DBUF8-1 (step 520). Next, CBUF7
-1, The queue in DBUF8-1 is sorted according to the priority order attached to the input / output instructions (step 5).
25). Then, the process returns to step 505.

If the queue is equal to or more than the threshold value in step 505, the command processing management section 75 confirms whether or not the input / output instruction can be processed (step 530). The command processing management unit 75 is performing other input / output processing,
If the processing is not possible, the process returns to step 505. When it is found that the command processing management unit 75 can perform new input / output processing, the number of input / output instructions that can be processed is
The input / output command commands are sent to the processing management unit 75 in the sorted order (step 535). After this, the process normally returns to step 505 to continue the input / output command. If the input / output processing is not continued, the input / output command processing is ended (step 545).

As can be seen from FIG. 6, in this embodiment, CBUF7-1 (or 7-2), DBUF8-1.
If the queue in (or 8-2) is less than or equal to the threshold value, the input / output management unit 70 transfers to the command processing management unit 75 C
The input reception of the input / output command from the CPU 1 is prioritized over the process of transferring the input / output command held in the BUF7-1 (or 7-2) and the DBUF8-1 (or 8-2). ..

Next, regarding the processing in the command processing management unit 75, each of the input command processing and the output command processing will be described.

FIG. 7 is a flow chart showing an output instruction processing (data reading) procedure of the command processing management section 75.

The output command from the CPU 1 is the input / output management unit 7
When sent from 0, the command processing management unit 75 starts output command processing (data reading from the secondary storage device 101 to the CPU 1) (step 600). The data address management table 50 is searched using the logical address of the output instruction specified by the CPU 1, and the data is requested by the instruction.
All the numbers of the disk drives whose number is equal to a certain multiplicity of data are searched (step 605). In step 605, first, the user number is confirmed, the logical address managed by the user number is searched from the area 105, and the storage destination of the data with the smallest history number is usually stored in the data corresponding to the logical address. The disk drive number of the disk drive is read from the area 130. (For example, the disk drive numbers # 1, # 2, and # 4 are read.) Next, the disk drive management table 60
Disk drive 1 that does not perform input / output processing
6, that is, the area 40 of the disk drive management table 60
All the disk drive numbers of the disk drives having no processing waiting instruction in which 2 is 0, that is, "000" in binary, are searched (step 610). Note that steps 605 and 6
In addition to this order, 10 can also perform parallel processing. Next, among the disk drives searched in steps 605 and 610, the disk drive having the requested data and the disk drive having no processing waiting instruction is selected (step 615). In the next step 620, it is confirmed whether or not the number of selected disk drives is equal to or larger than a predetermined threshold value l (l <multiplicity m). In order to enable the invention here, the multiplicity m must be 3 or more, and the total number of drives must be m or more.

If the number of disk drives selected in step 615 is less than or equal to the threshold value, waiting for the processing of the area 402 of the disk drive management table 60 among the disk drives having the data for the shortage. The one having the smaller number of input / output instructions is selected until the threshold value 1 is reached (step 625). Next, the logical address of the output command of the CPU 1 is converted into the physical address of the selected disk drive using the data address management table (step 630). At this time, output commands issued to the drive processor 17 are generated by the number of selected disk drives.

Next, the output command generated in step 630 is sent to the disk drive management section 85 (step 63).
5). When receiving a connection report from the disk drive management unit 85 with the disk drive 16 that has sent the output command (step 640), the disk drive management unit 85 sends to the other disk drives other than the first disk drive (eg, 16-2) connected first. The output command of is canceled and the processing is continued only for the disk drive connected first (step 645).

At the next step 650, other commands are processed until the data read from the disk drive 16 is completed and the completion of the output command processing is received from the disk drive management section 85 (steps 650, 655).
If the end report is received from the disk drive management unit 85, the processing status of the output command is checked and recorded (step 660), and the end of the output command is reported to the CPU 1 (step 665). When the above processing is completed, the command processing management unit 75 waits for the next input / output command sent from the input / output management unit 70 (step 670).

FIG. 8 shows a flowchart of input command processing (multiple data writing from the CPU 1 to the secondary storage device 101) in the command processing management unit 75.

The input command from the CPU 1 is the input / output management unit 7
When sent from 0, the command processing management unit 75 starts the input command processing (step 700). First, an input / output command is sent to the multiple write failure management unit 80, and the multiplicity and the number of stored history are received from the multiple write failure management unit 80 (step 705). Next, the data address management table 50
Further, a disk drive corresponding to the logical address of the input data designated by the CPU 1 and waiting for data satisfying the oldest history is searched for (step 710).
Next, the area 40 of the disk drive management table 60
A free disk drive whose number of waiting input / output instructions is less than a certain number, which is recorded in No. 2, is searched (step 715). Further, a free area of each disk drive is secured by the free area management table 55 by the amount of data (step 7).
20). Note that steps 710, 715 and 720
In addition to performing in this order, it is also possible to perform parallel processing. Further, step 710 is necessary for multiple writing in the secondary storage device 101 with a small free space, but may be used only for erasing the oldest history data in the secondary storage device with a sufficient free space. is there.

Next, of the empty disk drives 16 found in steps 715 and 720, the disk drives detected in both steps are selected (step 725).
It is confirmed whether or not the number of selected disk drives can be secured as much as the multiplicity received from the multiple write failure management unit 80 is satisfied (step 730).

If the disk drive selected in step 725 is not sufficient, the empty area searched in step 720 is the empty disk drive searched in step 715 and the number of input / output instructions exceeds a fixed number. A certain disk drive is selected (step 735), and further steps 725 and 735 are selected to check whether or not the number of disk drives can be secured for the multiplicity received from the multiple write failure management unit 80 (step 74).
0). Here again, when there are not enough disk drives, the lacking drive is selected from the drives having the data satisfying the conditions found in (step 710) (step 74).
5).

In this way, step 730 or 7
After satisfying 40 or securing the disk drive 16 in step 745, the logical address of the input command and the physical address of the selected disk drive are converted using the data address management table 50 (step 75).
0). At this time, the input command is generated by the number of selected disk drives and is issued to the drive processor 17 corresponding to the selected disk drive. The input command generated in step 750 is sent to the disk drive management unit 85 in step 755 (step 75
5) The other input / output commands are processed until the disk drive management unit 85 reports that the input command processing has been completed (steps 760 and 765).

When the completion report comes from the disk drive management unit, the result of step 710 is used to set the physical address of the history older than the predetermined history holding number received from the multiple write failure management unit 80 as the old physical address. (Step 770) The old address of the data is read from the data address management table 50, the area where the old history data is stored is registered in the empty area management table 55 as an empty area, and the empty area where the new data is stored is also registered. If there is an area, that area is deleted from the empty area management table 55 (step 775). Next, the new physical address of the data is read out and registered in the data address management table 50 (step 780). Next, the processing status of the input command is checked and recorded (step 785), and the end is reported to the CPU 1 (step 790). When the above processing is completed, the command processing management unit 75 waits for the next input / output command sent from the input / output management unit 70, as in the case of the output command (step 795).

FIG. 9 shows a flow chart of input / output command processing in the disk drive management unit 85.

First, the disk drive management unit 85 causes the command processing management unit 75 to send a command to each drive processor 17
The process is started by receiving an input / output command for -1 to 17-n (step 800). When the disk drive management unit 85 receives the input / output command from the command processing management unit 75, first, the disk drive management table 6
0 is searched, and the number of input / output instructions waiting for processing (area 402) of the disk device used is increased by one (step 805). The input / output command received from the command processing management unit 75 is sent to the disk drive control unit 90 in the drive processor 17 of the disk drive 16 to be used next (step 810). After that, it is confirmed whether or not the end report of the input / output processing is received from the drive processor 17 (step 815).

If the completion report is not received, the status of each disk drive is monitored next, and the disk drive 16-
1 to 16 to n, drive processors 17-1 to 17-n
Step (820,
825). If no failure has occurred, step 81
Return to 5. Here, the disk drives 16-1 to 16-
n, and any one of the drive processors 17-1 to 17-n has a failure, an area for the number of input / output instructions waiting for processing (area 402) in the disk drive management table 60 for the failed disk drive. A flag indicating that the disk drive is unusable is set to prohibit the use of the corresponding disk drive (step 830). Then, the failure is reported to the multiple write failure management unit 80 (step 835). If an I / O processing end report is received in step 815, the processing status is checked, and the number of input / output waiting for processing of the disk drive for which input / output processing has ended is decreased by one in the disk drive management table (step 84).
5). Finally, the end of the input / output command processing is reported to the command processing management unit 75, and the processing ends (step 847).
When the above processing is completed, the disk drive management unit 85
Waits for the next input / output command from the command processing management unit 75 (step 850).

FIG. 10 is a flowchart showing the processing procedure of the normal multiple write failure management unit 80 in the input / output command processing.

When an input / output command is sent from the input / output management unit 70, the multiple write failure management unit 80 retains the multiplicity and history according to a parameter given from the CPU 1 for each input / output command or determined by initial setting. The number is determined (step 965). Next, the multiplicity and the history holding number are sent to the command processing management unit 75 (step 970),
Next, it waits for an input command (step 975).

The same data multiple write control method of the present invention is also effective for data recovery when a failure occurs in a disk drive.

Next, with reference to FIG. 11, description will be given of processing when a failure occurs in the disk drive during the input / output processing. When the disk drive management unit 85 detects that one of the disk drives has failed (step 825 in FIG. 9) and receives the report (step 9).
00), the multiple write failure management unit 80 suspends the processing of the input / output instruction and reports the failure occurrence to the CPU 1 (step 905). Next, in the data address management table 50, the disk drive number or the physical address of the disk drive in which the failure has occurred is deleted and disabled (step 910). Next, the empty area management table 55
In that area, the disk drive number or physical address that caused the failure is deleted and disabled (step 9).
15). Then, it is confirmed whether the generated failure can be recovered (step 920).

If the fault can be recovered, the next step 925
Then, it is confirmed whether or not the failure recovery is performed. When performing failure recovery, the failure recovery process is performed as it is. The details will be described with reference to FIGS. 12 and 13 (step 930). When the failure recovery is not performed, the processing of the input / output instruction is restarted as it is (step 935). If it is determined that the failure recovery is not possible, then the CPU 1 is inquired about the use of the history data (step 940). When using the history data, it is confirmed whether or not the data having the old history number can be used (step 945). If available, the history number of the next oldest data is updated, and the number of history records is reduced accordingly. Then, the process proceeds to step 925. If the old data of the history number is not available, the data is considered to be lost and the CPU 1 is notified of the loss and the system is stopped (step 955).

Fault recovery processing (step 930 in FIG. 11)
FIG. 12 is a flowchart showing the detailed processing procedure of the above.

When it is determined in step 925 in FIG. 11 that failure recovery is to be performed, the multiple write failure management section 80 starts failure recovery (step 1000). Next, the data address management table 50 and the empty area management table 55 are reorganized (step 1010). If it is necessary to compensate for the lack of capacity, step 1005
An unused spare disk drive may be incorporated as shown in FIG. However, if the capacity EC of the empty area is sufficiently larger than the capacity of the data in the failed disk drive, the method of the present invention can recover from the failure without a spare disk device. Next, set the threshold value of the number of I / O commands waiting for processing, the data recovery capacity for one time, the I / O process priority time or the number of I / O processes, which is used to determine the priority control of the I / O process and the failure recovery process (Step 1015). In the present embodiment, as will be described below, the failure recovery processing is executed prior to the input / output processing, but if the number of input / output instructions in the processing waiting state exceeds a certain number, In order to prevent the number of input / output instructions from increasing abnormally, the input / output processing is preferentially executed. In other words, in this embodiment, data recovery processing can be performed while executing other input / output processing. Each parameter set in step 1050 is used to determine the switching of the process to be executed with priority. Next, the number of input / output commands waiting for processing is counted from the disk drive management table 60 (step 1020). This is performed by obtaining the sum of the number of input / output instructions waiting for processing corresponding to each disk drive number registered in the disk drive management table 60. As the next step, it is confirmed whether the number of processing input / output instructions is less than or equal to a threshold value (step 1025).

If the number of I / O commands waiting to be processed is equal to or greater than the threshold value, then the I / O process is executed for a fixed time set in step 1015 or for the number of I / O processes (step 1035), and then the step Proceed to 1040.

If the number of input / output instructions waiting to be processed is less than or equal to the threshold at step 1025, after performing the data recovery processing (step 1030), step 1040 is executed.
In step 1040, it is confirmed whether or not there remains a logical address for which data recovery has not ended. If there is any, the process returns to step 1020 to continue the failure recovery. When the data recovery processing is completed for all the failed logical addresses, the failure recovery ends and CP
Report to U1 (step 1045).

It is also possible to use the threshold value of the number of input / output instructions stored in the input / output buffer for the determination of switching the control to the input / output processing priority. 1020 is to count the number of input / output instructions stored in the input / output instruction buffer. Further, in the failure recovery here, it is considered that the failure recovery is performed without stopping the processing of the input / output instruction, but the failure recovery can be performed after the processing of the input / output instruction is stopped.

Details of the data recovery process (step 1030) in FIG. 12 will be described below with reference to the flowchart in FIG.

When the data recovery process is started (step 1100), first, the logical address of the data to be recovered is set (step 1105). The logical address of the data to be recovered is obtained by referring to the data address management table 50 and extracting the logical address registered in the data address management table 50 based on the disk drive number of the failed disk drive. Next, an output command is issued from the command processing management unit 75 for each of the logical addresses set in step 1105 (step 1110). Next, as described with reference to FIG. 7, the output command is processed to read the same data as the data stored in the failed disk drive from another disk drive (step 1115). Next, referring to the disk drive management table 60, a free disk drive number whose number of waiting input / output instructions is less than a certain number is searched for (step 1120), and then the free area of each disk drive is searched from the free area management table 55. Only the amount of data read in step 1115 is searched (step 112).
5). Note that the steps 1120 and 1125 can perform parallel processing in addition to this order. Next, the disk drive having the data satisfying the conditions, which was found in step 1120, and having the empty area found in step 1125 is selected (step 1130). In the next step 1135, it is confirmed whether the selected disk drive can secure the multiplicity.

If there are not enough disk drives, the disk drive having an empty area is selected from the disk drives having the number of input / output instructions exceeding a certain number in step 1140, and the process proceeds to step 1145. Next, the logical address of the data to be recovered is converted into the physical address of the disk device secured in step 1130 using the data address management table (step 1145). Next, the input command is sent to the disk drive management unit 85 (step 1150), and the data read in step 1115 is written in the disk drive secured in steps 1130 and 1140. Upon receiving a processing report of the input command from the disk drive management unit 85 (step 1155), the empty area in which the new recovery data has been input is set to the empty area management table 5
5 is deleted (step 1160) and the new physical address and logical address of the recovered data are registered in the data address management table 50 in association with each other (step 1165). Next, the processing status is checked and recorded (step 1170). Finally, the data recovery process ends (step 1175).

In this embodiment, the reading of the recovery data is
Multiple write failure management unit 80 to command processing management unit 7
5, the multiple write-in failure management unit 80 independently writes the read recovery data, but the multiple write failure management unit 80 also executes the recovery data write command processing. It is also possible to send an input / output command to the management unit 75 and have the command processing management unit 75 perform the processing from step 1120 to step 1150.

In the above-mentioned embodiments, the magnetic disk drive is listed in the column as the storage unit, but an optical disk drive, a floppy disk drive, or a semiconductor memory can be used in addition to this. Further, the present invention relates to the control unit 2 of the secondary storage device 101, the disk drive control units 90-1 to 90-n, and the disk drive 16-.
1 to 16-n and the like are stored in one housing, but in addition, the control unit 2 of the secondary storage device 101, the disk drive control units 901 to 90-n, and the disk drives 16-1 to 16-n.
It is possible to disperse 16-n on the network and apply the operation described in the present invention to them.

According to the embodiment of the present invention, when the input command is processed, if the disk drive in which the original data exists cannot be used for the processing of another input / output command, another available disk drive is used. Store the data in the empty area of. As a result, it is possible to improve the input / output processing performance because the CPU does not have to wait for an input command even though there is a usable disk drive. Also, when recovering from a disk drive failure, the data to be recovered is in a writable state without copying to multiple disk drives and writing that data to a specific disk drive. Since the recovery data is written to the disk drive at any time, it is possible to realize the failure recovery processing in which the deterioration of the input / output processing performance is suppressed to the minimum. Also, if the user specifies only the logical address of the requested data, the actual data address, data multiplexing, and data history update are converted and processed inside the device, so the user does not need to perform any extra operations. ..

Further, the secondary storage device to which the present invention is applied can easily add a disk drive.

That is, for example, it is assumed that the (n + 1) th disk drive is added to the secondary storage device 101 shown in FIG. 1 or 2. In this case, as shown by a broken line in FIG. 4, the disk drive number # n + 1, which is an empty area, is added to the empty area management table 55. On the other hand, as shown by the broken line in FIG. 5, the number of processing input / output instructions is zero, that is, the disk drive number # n + 1 of “000” in binary number is added.

When the control unit 2 executes an input / output command from the CPU 1 as shown in FIG. 8 in such a state, the added disk drive # n + 1 has a sufficient free area and is in a process waiting state. Since the number of output commands is small, it is more likely to be selected as a multiple write disk drive than other disk drives. Therefore,
The data capacity of the added disk drive # n + 1 increases rapidly, and the data capacity becomes equal to that of other disk drives.

As described above, the secondary storage device to which the present invention is applied is highly flexible with respect to both the addition of storage units and the reduction of storage units due to the occurrence of a failure.

[0083]

As described above, according to the present invention, data rearrangement is performed without burdening the user,
It is possible to realize a secondary storage device capable of improving the input / output processing performance and suppressing the performance degradation at the time of failure recovery.

[Brief description of drawings]

FIG. 1 is a configuration diagram showing a secondary storage device according to an embodiment of the present invention.

FIG. 2 is a configuration diagram showing a control unit 2 shown in FIG.

FIG. 3 is a configuration diagram showing an example of a data address management table of the present invention.

FIG. 4 is a configuration diagram showing an example of an empty area management table of the present invention.

FIG. 5 is a configuration diagram showing an example of a disk drive management table of the present invention.

FIG. 6 is a flowchart showing a processing procedure of an input / output management unit.

FIG. 7 is a flowchart showing an output instruction processing procedure of a command processing management unit.

FIG. 8 is a flowchart showing an input instruction processing procedure of a command processing management unit.

FIG. 9 is a flowchart showing a processing procedure of a disk drive management unit.

FIG. 10 is a flowchart showing a processing procedure of a normal multiple write failure management unit.

FIG. 11 is a flowchart showing a processing procedure of a multiple write failure management unit when a failure occurs.

FIG. 12 is a flowchart showing details of a failure recovery process.

FIG. 13 is a flowchart showing details of data recovery processing.

[Explanation of symbols]

1 ... CPU, 2 ... Control unit, 3 ... External interface path, 4 ... Interface port, 5 ... Channel path switch, 6 ... Channel port, 7 ... Command buffer,
8 ... Data buffer, 9 ... Internal data path, 10 ... Internal command path, 11 ... Microprocessor, 12 ... Management table, 13 ... Drive port, 14 ... Drive path switch, 15 ... Abitration processor, 16 ... Disk device, 17 … Drive processor,
18 ... Drive command path, 19 ... Drive data path.

Claims (25)

[Claims] 1. A method of performing multiple write of the same data to a plurality of storage units, wherein each of the first plurality of storage units is responsive to a data write command issued from a host device. Detects a data read command and a data write command issued in advance from the higher-level device, which is already in a processing wait state with respect to the storage unit, and based on the detection result, the preceding data in a processing wait state The above-mentioned first, which has no preceding read command or write data command or is in a processing waiting state, has a preceding data read command or data write command, and has a smaller total waiting time for processing the data read command or write command. Less than a plurality of second plurality of storage units, the selected second plurality of storage units Which each comprises writing data to request said data write command. 2. A method of reading data stored in multiple storage units in a second plurality of storage units, which is smaller than the first plurality of storage units, in a first storage unit, wherein the data is read from a host device. In response to a read command, for each of the first plurality of storage units, the number of storage units equal to the second plurality, in which the data requested by the command is stored, for that storage unit. The data read command and the data write command issued earlier from the higher-level device, which are already in the process waiting state,
Based on the detection result, among the second predetermined number of storage units, there is no data write command or data read command in the process waiting state, or a data write command or data read command in the process waiting state is issued. Selecting a third plurality of storage units that have less than the second plurality and have a lower total processing latency of the data read or data write command, and select the third plurality of storage units from among the selected third plurality of storage units. A method for reading data, comprising the step of first reading the data requested by the instruction from one storage unit that has become able to execute the data read instruction, and outputting the data to the host device. 3. A method of multiple-writing the same data to a plurality of storage units, wherein the storage address of each of the data in the first storage unit is registered in a data address management table. For each of the storage units, the free storage area address and the free capacity are registered in the free area management table, and for each of the plurality of storage units, the total number of read commands or write commands in the processing waiting state is stored in the storage unit management table. In response to a data write command from the host device, the free space management table and the storage unit management table are referenced, and there is a free space capable of storing the data requested by the write command, and A read command waiting for processing or a total number of commands less than the first plurality Select a second plurality of storage units, by referring to the data address management table, writing the data to the write command to each of the free space required by the second plurality of storage units said selected
A step of updating the data address management table, the free space management table, and the storage unit management table after writing the data. 4. The method according to claim 3, wherein in the step of selecting the second plurality of storage units, if the number of storage units having a free space capable of storing the write data is less than the second plurality. By referring to the address management table, the area of the data having the oldest history of the write data in the plurality of storage units is changed to a free area, and the storage unit including the area is stored in the second plurality of storage units. A multiple write method further comprising the step of selecting one. 5. The multiple write method according to claim 3, further comprising the step of further adding a storage unit and updating the free space management table and the storage unit management table in accordance with the addition of the storage unit. 6. A method of reading data stored in multiple storage units in a second plurality of storage units, which is less than the first plurality of storage units, in a plurality of storage units, the method comprising: The storage address, history level and number of multiple writes for each of the data are registered in the data address management table, and the total number of read or write commands awaiting processing for each of the plurality of storage units is registered in the storage unit management table. In response to a data read command from a higher-level device, the storage unit management table is referred to, and a third plurality, which has a smaller total number of read and write commands waiting to be processed, is smaller than the second plurality. A storage unit is selected, the read command is sent to each of the selected third plurality of storage units, and the selection is performed. In response to the first connection report from the third plurality of storage units, the read command sent to a storage unit other than the first connection report storage unit is canceled, and the first connection report storage unit A step of reading the data from the unit with reference to the data address management table and outputting the data to the host device. 7. Data recovery in a secondary storage device in which the same data is multiply stored in a second plurality of storage units, which is smaller in number than the first plurality of storage units, in the first storage unit. A method of registering a storage address and a data address management table for each of the data in the first plurality of storage units, and determining the free storage area address and the free capacity of each of the plurality of storage units. The free space management table is registered, the total number of read-wait and write commands for each of the plurality of storage units is registered in the storage unit management table, and the storage unit management is performed when a failure occurs in a storage unit. The table is updated to disable the failed storage unit, and the data address management Data having the same contents as the data used for recovery of the data (data to be recovered) in the storage unit in which the failure has occurred by referring to the table, and determining the data held in the normal storage unit, and managing the free space. Referring to the table and the storage unit management table, a storage unit having a free space capable of storing the data to be recovered and having the smallest total number of read commands or write commands waiting for the processing is selected, and the data is stored. A step of writing normal data used for the recovery in the selected storage unit with reference to an address management table. 8. The method according to claim 7, wherein in the step of deciding the data to be restored, it is decided to perform data restoration using history data, and the history degree of data in the data address management table is lowered by one. Data recovery method characterized by. 9. The storage unit according to claim 1, wherein:
A multiple write method that is a disk drive. 10. The data reading method according to claim 2, wherein the storage unit is a disk drive. 11. The multiple write according to claim 1, wherein the selecting includes a step of selecting the second plurality of storage units according to the total number of read commands or write commands in the processing waiting state in each of the storage units. Method. 12. The multiple write according to claim 2, wherein the selecting includes a step of selecting the second plurality of storage units according to the total number of read commands or write commands in the processing waiting state in each of the storage units. Method. 13. The storage device according to claim 1, further comprising the step of searching for a free storage capacity for each of the plurality of storage units in response to the write command from the host device. The step of selecting a unit includes a step of selecting the second plurality of storage units from the storage units having a free capacity capable of storing the data output from the higher-level device based on the search result. .. 14. A control device for performing multiple writing of the same data to a plurality of storage units, said means for receiving a data write command from a higher-level device, and a device for responding to the input of said write command in said receiving means. A means for detecting a read / write command from the host device in a processing waiting state for each of the plurality of storage units, and a processing wait time for the read / write command from the host device based on the detection result. It is characterized in that it includes means for selecting a small number of storage units by a predetermined number smaller than the number of the plurality of storage units, and means for writing the data output from the higher-level device to the selected storage units, respectively. Data multiple writing method. 15. A control device for reading out data stored in multiplex in a first predetermined number of storage units in a plurality of storage units, said control device comprising: means for receiving a data read command from a host device; In response to the read command,
For each of the plurality of storage units, means for detecting a read / write command from the host device in a processing wait state, and a low processing wait time for a read / write command from the host device based on the detection result. Means for selecting a second predetermined number of storage units less than the first predetermined number, means for sending the read command to each of the selected storage units, and a first connection report from the selected storage unit. In response, means for canceling the read command to a storage unit other than the storage unit that reported the connection first, and means for reading the data from the storage unit that reported the connection first and outputting the data to the host device. A control device comprising: 16. A control device for multiple-writing the same data to a plurality of storage units, managing the storage address, history degree, and the number of multiple writes for each of the data in the plurality of storage units. A data address management table, a free area management table that manages the free storage area address and free capacity of each of the plurality of storage units, and the number of read and write commands waiting for processing of each of the plurality of storage units. A storage unit management table to be managed, a means for receiving a data write command from a host device, and in response to the write command, the free space management table and the storage unit management table are referred to and output from the host device. It has free space to store the data, and Means for selecting a predetermined number of storage units having a small number of waiting read and write commands, and referring to the data address management table, store the data output from the host device in the empty areas of the selected storage units. A control device comprising: a writing unit; and a unit for updating the data address management table, the free space management table, and the storage unit management table after writing the data. 17. The control device according to claim 16,
The means for selecting a predetermined number of storage units refers to the address management table and selects a plurality of storage units if a predetermined number of storage units having a free capacity capable of storing the data output from the host device cannot be selected. A control device characterized in that an area of data having the oldest history degree of the data in the storage unit is changed to a free area. 18. A control device for reading out data stored in multiplex in a first predetermined number of storage units in a plurality of storage units, the control device for each of the data in the plurality of storage units. A data address management table that manages a storage address, a history level, and the number of multiple writes, a storage unit management table that manages the number of read-waiting and write-commands for each of the plurality of storage units, and a data read command Means for receiving from the device and, in response to the read command, refer to the storage unit management table and select a second predetermined number of storage units with a small number of read and write commands waiting for processing that is smaller than the first predetermined number. And means for sending the read command to the selected storage unit, respectively. Responsive to a first connection report from the selected storage unit, means for canceling the read command to a storage unit other than the first connection report storage unit, and from the first connection report storage unit And a unit for reading the data with reference to the data address management table and outputting the data to the higher-level device. 19. A control device in a secondary storage device in which the same data is multiply stored in a predetermined number of storage units in a plurality of storage units, wherein each of the data in the plurality of storage units is: With respect to each of the plurality of storage units, a data address management table that manages the storage address, the degree of history, and the number of multiple writes,
A free area management table that manages the free storage area address and free capacity, a storage unit management table that manages the number of read and write commands waiting to be processed for each of the plurality of storage units, and a failure occurs in a certain storage unit. To detect the failure, update the storage unit management table to disable the failure storage unit, and, in response to the occurrence of the failure storage unit, refer to the data address management table for recovery. A means for determining data, and having a free capacity capable of storing the data to be recovered by referring to the free space management table and the storage unit management table in response to the occurrence of the failed storage unit, and A hand to select a predetermined number of storage units with a small number of read and write commands waiting for processing. And a unit for writing the data to be restored to the selected storage unit by referring to the data address management table, and the data address management table and the free space management table after writing the data to be recovered. And a means for updating the storage unit management table. 20. The control device according to claim 19, wherein
The control device, wherein the means for deciding the data to be restored decides to perform the data restoration by using the history data, and lowers the history degree of the data in the data address management table by one. 21. The control device according to claim 14, wherein:
The control device, wherein the storage unit is a disk drive. 22. The control device according to claim 15, wherein
The control device, wherein the storage unit is a disk drive. 23. The control device according to claim 14, wherein:
The control device is characterized in that the processing waiting time is determined according to the number of read and write commands from the host device. 24. The control device according to claim 15, wherein
The control device is characterized in that the processing waiting time is determined according to the number of read and write commands from the host device. 25. The control device according to claim 14, wherein:
Further, in response to the write command from the host device, the device includes means for searching a free storage capacity for each of the plurality of storage units, and means for selecting a predetermined number of storage units is output from the host device. The control device is characterized in that a predetermined number is selected from a storage unit having a free capacity capable of storing the data.