JP2702278B2 - Disk drive device - Google Patents

Description

Description: TECHNICAL FIELD The present invention relates to a disk drive using a disk array.

[Related Art] In recent years, a disk array in which many small disk drives are arranged has been devised. This is to improve the data transfer speed and reliability by switching and using each disk drive.

A technique using this disk array will be described with reference to the drawings.

FIG. 13 shows an example of a drive group having an array structure.

This device is a hard disk controller 301-304
And disk drives 310-312,320-322,330-332,340
342, that is, a total of four hard disk controllers and 16 disk drives.

Now, one logical group in the array disk is
Disk drives 310, 320, 330, 340, disk drives 311, 321, 331, 341 and disk drives 312, 322, 332, 3
There are three groups of four, each with 42.

Of the disk drives belonging to each logical group, the drives under the hard disk controllers 301 and 302 are used as data storage drives, the drives under the hard disk controller 303 are used as redundant data drives, and the drives under the hard disk controller 304 are used as spare drives. Assigned to

The drive group surrounded by a dotted line a indicates one group.

Now, when a failure occurs in the disk drive 310, the disk drive 340, which is set as a spare, is set as a switching target and is switched to the disk drive 310.

After switching, the relevant logical group (hereinafter referred to as group)
Is composed of disk drives 320, 330, and 340 (a drive group surrounded by a dotted line b). Thereafter, when a failure occurs in the disk drive 320, the disk drive is similarly switched to the disk drive 341 that is also assigned as a spare.

As a result, the group is assigned to the disk drives 330, 34
0,341 (a drive group surrounded by a dotted line c).

 Another example will be described.

FIG. 14 shows only two of the group of drives having an array structure. Group A includes disk drives 350a to 355a, and group B includes disk drives 350b to 355b. The disk drives 350a to 353a and the disk drives 350b to 353b are allocated as data storage drives. Further, the disk drives 354a, 355a, 354b, 355b are allocated to redundant data drives.

In this case, even if a failure occurs in the disk drive, data is not lost if the number of drives in one group is two or less.

[Problems to be Solved by the Invention] However, as shown in FIG. 13, switching of the disk drive when a failure occurs in the disk drive according to the prior art is performed by sequentially switching the disk drive initially set as a spare. In some cases, a plurality of drives constituting a group after switching exist under the same hard disk controller for use as a disk drive to be switched. As a result, at the same time, the number of drives that can be accessed is reduced, leading to a decrease in the performance of the group.

More specifically, in the above case, two disk drive devices 340 and 341 are allocated to one hard disk controller 304. Therefore, in the group, only one disk drive 330 and one of the disk drives 340 or 341 can be accessed at a time, that is, only two disk drives.

Therefore, a single drive can only be accessed sequentially, leading to a reduction in performance.

In the example shown in FIG. 14, if a disk drive of one group fails in the same group, the data cannot be restored. There is a case where the drive is normal and data can be restored even if two disk drives fail. In other words, there is a problem that a group in which data loss is likely to occur and a group in which data loss is low coexist, and the reliability as a whole decreases.

More specifically, if a failure occurs in the disk drive 350a and the disk drive 351a, data cannot be restored in the group A if at least one drive fails. On the other hand, in the group B, even if two more drive failures occur, data can be restored, and the reliability of each group varies.

Further, even when the performance and the reliability required for each group are different, the switching has not been performed in consideration of them. In other words, a group required to have high performance is composed of a plurality of disk drives under the same hard disk controller, and a group required to have high reliability has a high risk of data loss.

An object of the present invention is to dispose a disk drive in a position such that the number of drives that can be accessed at one time does not decrease even after the disk drive switching when a failure occurs in the disk drive. The purpose is to provide a disk drive device to be selected.

Another object is to distribute the risk by sharing the risk of data loss between groups due to a disk drive failure from a low-risk group to a high-risk group. To provide a disk drive device.

In addition, another purpose is when a disk drive fails.
Provided is a disk drive device for determining whether or not to switch disk drives based on user instruction information required for each group, such as performance and reliability, and when switching, selecting an optimum switching target that meets the requirements. It is to be.

Also, the trigger for switching the disk drive is
An object of the present invention is to provide a disk drive device having a function that can be set for each group.

[Means for Solving the Problems] The present invention has been made to achieve the above object.
According to one aspect, in a disk drive device including a disk drive group having a plurality of logical drive groups including a plurality of drives and control means for controlling the drives of each group, the logical drive group includes a spare drive. A first mode for switching the failed drive to a spare drive in the same group as the failed drive or a spare drive controlled by the same control means as the control means for controlling the failed drive; Among the drives controlled by the same control means as the control means for controlling the failed drive, a drive belonging to a group in which an unused spare drive exists is set as a drive to be switched, and the drive to be switched is set as the drive to be switched. Switch between the drive and a spare drive in the same group And a second mode for switching between the failed drive and a drive to be switched controlled by the same control means as the failed drive. If a failure occurs in any of the drives, the failure drive is included in the same group as the failed drive. When there is a spare drive or a spare drive controlled by the same control means as the control means for controlling the failed drive, the first mode is entered and the drive is switched. A disk drive device having a function of entering a second mode and switching a drive.

According to another aspect, in a disk drive device including a disk drive group having a plurality of logical drive groups each including a plurality of drives, and control means for controlling the drives of each group, the control means includes: In the event of a drive failure, check the margin, which is the number of drives until data loss occurs,
There is provided a disk drive device characterized in that a drive belonging to a group having a large margin is switched so as to belong to a group having a small margin.

As another aspect, in a disk drive device including a plurality of drives and control means for controlling each drive, the control means has a function of switching a drive to be used, and has a function of switching only a predetermined time zone. And a disk drive device having a function of performing the switching.

In each of the above aspects, the drives constituting the group are logically such that drives belonging to the same logical group are located in the same row, and drives controlled by the same control means are located in the same column. Preferably, they are arranged in a matrix. The drives may include a data storage drive for registering data and a redundant data drive.

The control means may include one or more of the following parameters.

The data storage drives that make up each group,
It consists of a physical address of the redundant data drive and a failure flag indicating the status of the drive. Group table.

A spare drive management table including the current number of spare drives, the physical address of the spare drive, and an invalid flag indicating whether the spare drive is unused.

A physical drive management table showing a physical address and an attribute of a drive of the address. The physical drive management table includes a failure flag indicating whether the drive is normal or a failure, a group number to which the drive belongs, and whether the drive is a data storage drive, a redundant data drive, or a spare drive. It is composed of the following drive identifiers.

Requirement level management table showing the required performance and reliability levels for each group. The required level management table includes a performance level required for the group, the number of failed drives in the group, and a reliability level required for the group.

6 is a switching scheduling table for instructing a switching operation at the time of a drive failure for each group.

A switching reservation table in which a switching operation is reserved if switching is not performed immediately when a drive fails. The switching reservation table is set for each group and includes a failed drive address and a registration flag.

[Operation] When detecting a failed drive, the control means determines whether or not the drive is currently switched. this is,
The determination is made by obtaining the group number from the physical drive management table from the address of the failed drive, further obtaining the switching trigger of the group from the switching scheduling table, and comparing it with the current time. At this time, the failure flag in the physical drive management table is turned on at the same time. If the current switching is to be performed, the switching is performed immediately. If not, the address is registered in the switching reservation table corresponding to the group and the registration flag is turned on. The registered failed drive is monitored at a certain period, and when the switching time has been reached, the registration flag is turned off and switching is performed.
Thus, switching can be performed in accordance with the trigger set for each group.

When the switching is performed, the following three states exist depending on the state of the spare drive and the like.

Note that the first state and the second state correspond to the first mode, and the third state corresponds to the second mode.

The first state is a state in which a spare drive exists and exists in the same row or the same column as the address of the failed drive. The second state is that a spare drive exists but is located in the same row or There is no spare drive in the same row, and the third state is where there is no spare drive.

The current state is determined in the following procedure.
First, find the number of spare drives in the spare drive management table,
If the number of spare drives is 0, it is determined to be in the third state.
If the number of spare drives is other than 0, it is the first or second state. The first or second judgment is that, assuming that the failed drive address is (l, m), a spare drive address in which the invalid flag is off in the spare drive management table has l in the row or m in the column. If something exists, it is determined to be in the first state, otherwise it is determined to be in the second state.

In the first state switching operation, a data storage drive and a redundant data drive of the group are obtained from the group table based on the group number of the failed drive, and the data of the failed drive is restored from the data of those drives. , Copy to spare drive. Then, the failed drive address in the group table is changed to the spare drive address, the validity flag of the spare drive is turned off, and the number of spare drives is decremented by one. Further, the group number and the data identifier of the failed drive are copied to the switched spare drive in the physical drive management table.

In the second state, if the drive is simply switched to the spare drive, the performance of the group deteriorates after the switch. Here, the performance level required for the group is determined from the required level management table, and if the performance requirement is low, the drive is directly switched to the spare drive. The switching operation is the same as in the first state. When the demand for performance is high, the process starts by searching for a drive to be switched. A normal drive which has a spare drive in the same row and exists in the same column of the failed drive is searched. This is to find a spare drive address whose valid flag is ON in the spare drive management table. If this is (i, j) and the address of the failed drive is (l, m), the physical drive management table determines whether the address (i, m) is a normal drive. Becomes a switching target. If a failure occurs, a next spare drive is obtained, and the process is repeated until a normal drive satisfying the above conditions is found. As a result, if there is no drive that satisfies the above condition, the spare drive is set as the switching target. The switching operation at this time is the same as the switching operation in the first state. The switching operation when there is a drive satisfying the condition will be described. The drive to be switched (hereinafter C, DRV) is first replaced with a spare drive (hereinafter SD)
RV). As in the first state, the data of the failed drive (hereinafter, B.DRV) is restored and copied to C.DRV. Next, in the group table, set the S.DRV address
Update to C.DRV address and update B.DRV address to C.DRV address. In the spare drive management table, the valid flag of the S.DRV is turned off, and the number of spare drives is decremented by one. Next, the group number and drive identifier of 2, C.DRV are copied to S.DRV in the physical drive management table, and then the group number and drive identifier of B.DRV are copied to C.DRV. Thereby, the performance of each group by switching using the spare drive at the time of drive failure can maintain the same performance as before switching. Further, it is possible to provide drive switching suitable for the performance requirements of each group.

In the third state, since the failed drive is not recoverable, the risk of data loss is distributed according to the reliability level required for the group. As a distribution method, the number of failed drives in the group is incremented by 1 according to the request level management table, and is compared with the reliability level. When the demand for reliability is high and the margin before data loss is small, the drive is more flexible than the group having a large margin for data loss and a low demand for reliability. this is,
Based on the reliability level and the number of failed drives, a group number to be interchanged is determined, and a drive in the same row as the failed drive is determined from the group and is set as an interchange target. This is to prevent performance degradation after the interchange. If there is no drive in the same row, the drive in any row is targeted. In the switching operation for interchange, the data of the failed drive is restored and copied to the switching target drive as in the first state. Next, in the group table, the address of the failed drive is updated to the address of the switching target drive, and the failure flag of the switching target drive is turned on. Next, the group number and the drive identifier of the failed drive are copied to the switching target drive from the physical drive management table. In the request level management table, the number of failed drives in the group including the failed drive
In step 1, the number of failed drives in the group including the switch target drive is incremented by one. As a result, it is possible to achieve the distribution of the risk level that matches the reliability required for the group.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

FIG. 1 shows a computer system including a disk drive device to which the present invention is applied.

This computer system has a central processing unit CPU60.
And the disk array controller 70 and the disk array device 80
And a disk drive device mainly composed of

The disk array control device 70 controls the disk array device 80 in accordance with an instruction from the CPU 60.

FIG. 2 shows the internal configuration of the disk array controller 70.

The microprocessor unit 74 executes the programs stored in the random access memory 75 while sequentially decoding them, and controls the entire disk array controller 70. The channel control circuit 71 controls data transfer with the CPU 60. The control circuit 72 controls data transfer with each drive. The data buffer 73 is used when transferring data between the channel control circuit 71 and the control circuit 72. The redundant data creation circuit 76 adds redundant data to the data sent from the CPU 60. clock
77 is provided in this subsystem.

At the time of reading, data read from each drive of the disk array device 80 is temporarily stored in the data buffer 73, and after synchronization, the channel control circuit 71
It is configured to be sent to U60.

FIG. 3 shows a drive configuration of the disk array device 80.

The data transfer control circuits 81 to 87 are for transferring data to and from the disk array control device 70. Each of the data transfer control circuits 81 to 87 includes four drives 81a.
To 81d, 82a to 82d, ..., 87a to 87d are connected.

The drive group under the data transfer control circuits 81, 82, 83, 84 is a data storage drive, and the drive group under the data transfer control circuits 85, 86 is a redundant data drive. The subordinate drive group is assigned as a spare drive.

In addition, this drive group includes a data recovery group (hereinafter referred to as a group), drives 81a to 87a, and drives 81a to 87a.
81b to 87b, drives 81c to 87c, and drives 81d to 87d. Hereafter, the groups Ga, Gb, Gc, G are grouped in the order from the one closer to the data transfer control circuits 81 to 87.
called d.

In addition, the addressing of each drive is regarded as a matrix, and the arrangement of the drives is regarded as a matrix.
(0,0) to (3,6) are addresses.

The microprocessor unit 74 of the present embodiment is configured to select a drive most suitable for satisfying the requirements and the like in consideration of reliability and the like required for each group and drive, and to switch the drive. . Specifically, the random access memory 75 or the like is provided with various tables to be described later in which various requests, conditions, and the like are input in advance, and selects a drive to be switched while referring to the tables.

This table will be described with reference to FIGS.

The group table 90 shown in FIG. 4 has the address information of the drives constituting each group.

In this table, row 100 is group Ga, row 101 is group
Gb, row 102 corresponds to group Gc, and row 103 corresponds to group Gd. In addition, drive address information 91 to 94 for data storage and drive address information 95 and 96 for redundant data are provided for each group.

Each of the drive address information 91 to 94 includes a failure flag 104 indicating that the data is inaccessible due to a drive failure, a row address 105 of the drive,
And a column address 106.

 Next, FIG. 5 shows the spare drive management table 110.

This spare drive management table 110 shows the address information of the current spare drive. This is composed of a valid flag 111 indicating that the spare drive has not been used, and a row address 112 and a column address 113 of the spare drive. Further, it has a spare drive number 114 indicating the current number of spare drives.

 FIG. 6 shows the physical drive management table 120.

The physical drive management table 120 shows management information of a drive having an address indicated by a matrix (I, J) consisting of numbers I and J shown on the upper side and the left side of the table in the figure. It is to show that it is.

For each drive, a failure flag 121, an identifier 122 indicating whether the drive is a data storage drive, a redundant data drive, or a spare drive, and a group number 123 to which the drive belongs are included. have.

 FIG. 7 shows the request level management table 130.

The request level management table 130 indicates the required level of performance and reliability of each group.
Is group Ga, row 132 is group Gb, row 133 is group G
c, row 134 corresponds to group Gd.

Each group includes a performance level 136 required for the group, the number of failed drives 137 in the group, and a reliability level 138 required for the group.

The performance level 136 defines “0” as “low” and “1” as “high”. When the performance level 136 is high, the switching due to the disk failure is switched to a drive that does not cause performance degradation even after the switching, and when the performance level 136 is low, it is simply switched to the spare drive.

In addition, the reliability level 138 indicates that “0” is “low”,
“1” is defined as “high”. When the number of failed drives in the group having the higher reliability level 138 becomes two, the drive is switched from the group having the lower reliability level 138 to accommodate the drive. Switching is also performed under the above conditions for a group having a low reliability level 138. The drive to be switched is selected from a group having a low reliability level 138.

FIG. 8 is a switching scheduling table 140. This table is used to specify when to perform drive switching for each group.

In the switching scheduling table 140, the row 141 corresponds to the group Ga, the row 142 corresponds to the group Gb, and the row 143 corresponds to the group Gc.
Meanwhile, row 144 corresponds to group Gd. The data of each group includes a parameter 145 and a start time 146.
And a final time 147.

When the value of the parameter 145 is 0, the drive switching is executed immediately. The value of parameter 145 is 1
In the case of, drive switching is executed only in the time zone specified by the start time 146 and the end time 147. When the value of the parameter 145 is 2, only the day of the week indicated by the start time 146 to the last time 147 is executed.
When the value of the parameter 145 is 3, the process is executed only on the day specified by the start time 146 and the end time 147.

 FIG. 9 shows the switching reservation table 150.

When the value of the parameter 145 is not 0, that is, for a failed drive that does not immediately execute the drive switching, the switching reservation table 150
This is for making a reservation for switching in a time zone specified by the start time 146 and the final time 147 of 0.

The reservation is performed by registering the row address 152 and the column address 153 of the failed drive and turning on the registration flag 151.

Further, when the switching of the drive is completed, the registration of the drive is deleted by turning off the registration flag 151.

Next, the search operation for the drive to be switched when the drive (x, y) fails will be described with reference to FIGS. 10 (a), (b), (c), and (c).
This will be described with reference to the flowchart shown in FIG.

First, a group to which the failed drive (x, y) belongs is obtained using the physical drive management table 120 (step 2).
00). Next, the switching execution time of the group is obtained from the scheduling table 140 (step 201).

As a result, it is determined whether or not the parameter 145 is 0, that is, whether or not the switching is to be performed immediately (step 20).
2) If there is no need to switch immediately, the switching is reserved by the processing of steps 220 and 221 shown in FIG. 10 (d).

In step 220, the microprocessor unit 7
Step 4 searches for an area where the registration flag 151 of the switching reservation table 150 is off. Subsequently, the registration flag 151 of the area is turned on, and the address of the failed drive is registered (step 221).

For the failed drive for which the reservation has been made, thereafter, for example, at a certain fixed period or the like, it is determined by the clock 77 whether or not the current time is between the start time 146 and the final time 147. , With the logic following step 203,
Perform switching.

If the switching is to be executed immediately in step 202, the spare drive management table 110 is searched and the valid flag 1
It is determined whether 11 is ON, that is, whether or not there is a usable spare drive (step 203). As a result, if there is at least one available spare drive, subsequently, at step 204, it is determined whether any of the available spare drives is located at a position that does not cause performance degradation. Judge at 205.

In step 204, whether or not a spare drive exists in the same row (x) as the failed drive is determined by a spare drive management table 11
The determination is made by searching for a row address 112 of 0. If there is, the process proceeds to step 213, and the searched drive is switched as the switching target drive.

If there is no spare drive in the same row, it is determined whether a spare drive exists in the same column (y) by searching the column address 113 of the spare drive management table 110 (step 205). If there is, the process proceeds to step 212, and the searched drive is set as a switch target drive, and
Switch.

If there is no spare drive in either the x-row or the y-column, simply switching to the spare drive does not prevent the performance degradation.

So, to know the performance required of the group,
The performance level is obtained using the performance level 136 of the required level management table 130 (step 206), and the value is confirmed (step 207).

As a result, when the performance level 136 is 0, that is, when the required performance is low, any one of the existing spare drives is set as the drive to be switched, and the drive is switched (step 211). On the other hand, when the performance level 136 is 1, that is,
When the required performance is high, the process proceeds to step 208.

By the way, in order to prevent performance degradation, it is necessary not to reduce the number of parallel drives. Therefore, it is preferable to select the drive to be switched from the same column (y) as the failed drive. However, at this time, care must be taken to prevent the group including the selected drive from deteriorating in performance. Therefore, in step 208, a drive satisfying such a condition is searched.

Specifically, for a drive in the y column of the physical drive management table 120, in other words, for a drive in the same column as the failed drive, it is determined whether or not there is a spare drive in each of the same rows.
The determination is made using the identifier 122 of the physical drive management table 120.
For example, if the failed drive is (2,1) and the spare drive is (6,1)
If it exists in (3), (2,3) is a drive satisfying the above conditions.

When a drive is selected in step 208, the process proceeds to step 209.

In step 209, first, the drive determined in step 208 and the spare drive in the same row as the drive are switched. And then the failed drive and step 20
The drive determined in step 8 is switched (step 210).

As described above, first, the other drive in the same column as the failed drive is switched to the spare drive in the same row as the other drive, and then, the failed drive is switched to the other drive to thereby become the same as the failed drive. It is possible to switch to the drive in the row.

By adopting this method, it is possible to provide a group requiring high performance to maintain performance in the event of a drive failure.

 The actual switching operation will be described from step 230.

Next, a description will be given of the case where it is determined in step 203 that there is no spare drive with reference to FIG. 10 (c).

In step 214, 1 is added to the value of the number of failed drives 137 in the request level management table 130. As a result, the number of failed drives is 1
37 indicates the risk of data loss of the group after the occurrence of the failure.

In this embodiment, redundant data drives are assigned to two groups.
Therefore, the margin up to the data loss is two failures. Therefore, in step 215, the number of failed drives is determined. If the number of failed drives is two or less, it is determined that the risk of data loss is low, and the operation is terminated as it is.

On the other hand, when there are two failed drives, that is, when there is no margin, the risk of data loss is very high, so the drive to be switched is selected so that the risk is distributed to the entire disk array device 80 (step 216).

The logic for optimizing the drive selection in step 216 will be described later in step 240 in FIG.

Subsequently, the failed drive is switched to the drive selected in step 216 (step 217).

As a result, in the group obtained in step 200, that is, the group to which the failed drive belongs, one drive has been exchanged from the group to which the drive selected in step 216 belongs. Accordingly, in step 218, the group to which the failed drive belongs decreases the value of the number of failed drives 137 by one, while the group on the interchange side increases the value of the number of failed drives 137 by one (step 219).
Then, the operation ends.

Next, the drive switching operation will be described with reference to the flowchart of FIG.

This operation is performed in steps 209, 210, 211, 212, 213, and 217.
It is applied to.

In the following description, an operation when switching between the drive A having the address (x, y) and the drive B having the address (x ', y') will be described.

There are three types of combinations of drives that perform this operation: a normal drive and a spare drive, a failed drive and a spare drive, and a failed drive and a normal drive.

After the start of the operation, the microprocessor unit 74 first determines whether any of the drive A and the drive B to be switched is a failed drive (step 230). If any of the failed drives is a failed drive, the failure flag 121 of the failed drive in the physical drive management table 120 is first turned on, and the failure flag 104 corresponding to the failed drive in the group table 90 is further turned on.
Is also turned on (step 231). Then, the process proceeds to step 232.

On the other hand, if it is determined in step 230 that the failed drive is not included, the process directly proceeds to step 232.

In step 232, the identifier 122 and the group number 123 of the drive A and the drive B in the physical drive management table 120 are exchanged. Thus, the switching as the physical address ends.

Subsequently, it is determined whether or not a spare drive is included (step 233). If it is included, the process proceeds to step 234. If not, the process proceeds to step 238.

In step 234, the contents of the row address 112 and the column address 113 of the spare drive management table 110 are changed to a normal drive or a failed drive address to be switched, and
The contents of the failure flag 104 of the group table 90 are also copied to the valid flag 111 of the spare drive management table 110.

Subsequently, it is determined whether the valid flag 111 is 1 (step 235). If the valid flag 111 is 1,
That is, when the spare drive and the failed drive are switched, the value of the spare drive number 114 is reduced by 1 (step 23).
6), proceed to step 237. On the other hand, if the valid flag 111 is 0, that is, if the spare drive and the normal drive are switched, the process directly proceeds to step 237.

In step 237, the row address 11 of the spare drive
2. The column address 113 is copied to the row address 105 and the column address 106 of the drive to be switched in the group table 90, and the switching operation ends.

On the other hand, if it is determined in step 233 that the spare drive is not included, the address information of the drive to be switched, that is, the failure flag 10
4. The row address 105 and the column address 106 are exchanged with each other (step 238), and the switching operation ends.

By the above steps 234 to 238, the switching of the drive addresses constituting one group and the address information of the spare drive is completed.

Next, a method of selecting an optimized drive performed in step 216 will be described with reference to the flowchart shown in FIG.

When the number of failed drives in the group becomes 2, the risk of data loss in this group is extremely high because the present system has redundant data for only two drives.

Therefore, it is necessary to first select a group that accommodates one drive. For that purpose, first, in step 240, a group whose reliability level 138 in the request level management table 130 is 0, that is, a group whose required reliability is low is searched.

This is because the drive from a group having a relatively low reliability requirement is provided.

Subsequently, it is determined whether or not a group having the reliability level 0 exists (step 241). On the other hand, if it does not exist, the process proceeds to step 244.

In step 242, a group in which the reliability level 138 is 0 and the number of failed drives is 0 is searched. This corresponds to the number of failed drives 137 of the group in the request level management table 130.
Is determined based on whether or not the value of is zero. Thereby, the group with the lowest risk can be found.

Subsequently, it is determined whether or not there is a group that satisfies the condition of step 242 (step 243). If there is, a group providing a drive is determined to be the group (step 247). If not, however, step 244
Proceed to.

In step 241 or step 243, if there is no group that satisfies the conditions required in each step, that is, if there is no unreliable group or if there is If a drive is present, proceed to step 244, as described above.

In step 244, first, the reliability level of the group including the failed drive is determined. As a result, when the reliability level is low, that is, when the value of the reliability level 138 is 0,
In the case of, it is determined that there is no switching target group (step 24)
8). Conversely, when the reliability level is high, that is, when the value of the reliability level 138 is 1, a group in which the number of failed drives is 0 is obtained (step 245).

Then, it is determined whether or not there is a group that satisfies the above condition, that is, a group with a high reliability level and a number of failed drives of 0 (step 246). The group is set as a switching target group. Conversely, if it does not exist in step 246, there is no group to be switched (step 248).

At steps 240 to 248 in FIG. 12, the presence / absence of a switching target group and, if it exists, at least one group number are determined.

Then, it is possible to determine which drive in the group is optimal to switch to by performing the same processing as in steps 204 to 208 in FIG. 10A for the drives in the group. it can.

As described in the above embodiment, when a failure occurs in a drive, it is necessary to select a switching drive that matches the performance and reliability required for each group, regardless of whether a spare drive exists or not. Can be. Therefore, the performance balance and the reliability balance of the entire disk drive device can be maintained.

[Effects of the Invention] As described above, according to the present invention, at the time of drive failure, if at least one spare drive exists, performance can be maintained even after switching. In addition, since the risk of data loss is distributed to all the drives even when there is no spare drive, the reliability is improved because the drives are interchanged. Further, a time zone or the like in which the above processing is performed can be designated, and it is possible to flexibly respond to a user request. Furthermore, the present invention has effects such as no change in hardware, realization with only a microprogram, and the like.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a computer system using a disk drive device according to one embodiment of the present invention, FIG. 2 is a block diagram showing a configuration of a disk array control device of this embodiment, and FIG. FIG. 4 is an explanatory diagram showing a configuration of a disk array device according to an embodiment of the present invention, FIG. 4 is a configuration diagram of a group table used in the embodiment, and FIG. 5 is a configuration of a spare drive management table used in the embodiment. FIG. 6, FIG. 6 is a configuration diagram of a physical drive management table used in this embodiment, FIG. 7 is a configuration diagram of a request level management table used in this embodiment, and FIG. 8 is switching scheduling used in this embodiment. Configuration diagram of the table,
FIG. 9 is a configuration diagram of a switching reservation table used in the present invention,
FIG. 10 is a flowchart showing a search procedure for a drive to be switched, FIG. 11 is a flowchart showing a switching operation procedure, and FIG.
12 is a flowchart showing a switching drive search operation for fractionating the degree of risk, FIG. 13 is an explanatory diagram showing a conventional disk array device, and FIG. 14 is an explanatory diagram showing the concept of a conventional disk array group. is there. 60: central processing unit, 70: disk array controller, 71: channel control circuit, 72: control circuit, 73: data buffer,
74: microprocessor unit, 75: random access memory, 76: redundant data creation circuit, 77: clock, 80: disk array device, 81 to 87: data transfer control circuit, 81a, b, c, d
~ 87a, b, c, d: drive, 90: group table, 91 ~ 94:
Drive address information for data storage, 95: drive address information for redundant data, 96: drive address information for redundant data, 100: row, 101: row, 102: row, 103: row, 104: failure flag, 105: row address , 106: column address, 110: spare drive management table, 111: valid flag, 112: row address, 113:
Column address, 114: number of spare drives, 120: physical drive management table, 121: failure flag, 122: identifier, 123: group number, 130: request level management table, 131: row, 132: row, 133: row,
134: Row, 136: Performance level, 137: Number of failed drives, 138: Reliability level, 140: Switching scheduling table, 141: Row, 14
2: line, 143: line, 144: line, 145: parameter, 146: start time, 147: last time, 150: switching reservation table, 151: registration flag, 152: line address, 153: column address, 301 to 304 :
Hard disk controller, 310-312,320-322,330
~ 332,340 ~ 342: disk drive, 350a, b ~ 355a, b: disk drive.

 ──────────────────────────────────────────────────続 き Continuation of the front page (56) References JP-A-2-236714 (JP, A) JP-A-2-214406 (JP, A) JP-A-58-22465 (JP, A) JP-A-4- 153727 (JP, A)

Claims (3)

(57) [Claims] 1. A disk drive device comprising: a disk drive group having a plurality of logical drive groups composed of a plurality of drives; and control means for controlling the drives of each group, wherein the logical drive group has a spare drive. A first mode for switching the failed drive to a spare drive in the same group as the failed drive or a spare drive controlled by the same control means as the control means for controlling the failed drive; Failed drive
Among the drives controlled by the same control means as the control means for controlling the failed drive, a drive belonging to a group having an unused spare drive is set as a drive to be switched, and the drive to be switched is the same as the drive to be switched. Switch to the group's spare drive, then
A second mode for switching between a failed drive and a drive to be switched, which is controlled by the same control means as the failed drive, wherein a failure occurs in any of the drives;
When there is a spare drive in the same group as the failed drive or a spare drive controlled by the same control means as the control means for controlling the failed drive, the first mode is entered and the drive is switched. A disk drive device having a function of entering a second mode and switching drives when a spare drive does not exist. 2. A disk drive device comprising: a disk drive group having a plurality of logical drive groups composed of a plurality of drives; and control means for controlling the drives of each group, wherein the control means comprises: When a drive failure occurs, a margin, which is the number of drives until data loss occurs, is checked, and a drive belonging to a group having a large margin is switched to belong to a group having a small margin. Disk drive device. 3. A disk drive device comprising a plurality of drives and control means for controlling each drive, wherein said control means has a function of switching a drive to be used, and has a function only in a predetermined time zone. A disk drive device having a switching function.