JP2002304331A - Device and method for controlling redundant pass - Google Patents

Abstract

PROBLEM TO BE SOLVED: To gain an access also to a reserved logic disk by using an alternative pass. SOLUTION: When a retry processing is abnormally completed because the logic disk 13 is reserved by an initiator 5, a pass redundant driver 3 issues a forced reserve command from the initiator 6 of the alternative pass. When the forced reserve command is issued, the controller 12 re-sets the logic disk 13 in the state of reserve by the initiator 6 of the alternative pass.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention performs retry processing on a logical disk using an alternative path including an initiator when a failure occurs in an I / O access path.
The present invention relates to a redundant path control device and method.

[0002]

2. Description of the Related Art A path redundancy driver 3 'is a component of an I / O access path, that is, an HBA (Host Bus).
Adapter) 5, 6, Interface cable 3
Even when a failure (failure) occurs in the controllers 1, 32, the controllers 11 ′, 12 ′, etc., a retry process is performed on an alternative path so as not to affect the operation of the application 7 operating on the host computer 1. It provides a means. That is, the I / O path redundancy for the logical disks 13 to 15 can be realized by the redundant disk array device 10 and the software (path redundancy driver 3 ′) operating on the host computer 1.

[0003] An arbitrary logical disk 13 used by an application 7 running on the host computer 1
15 to 15 may be occupied (reserved) so that they cannot be accessed from another application (not shown) or another host computer. Generally, this occupation state is determined by the initiator (here, HBA
Is released by the release command from the corresponding ()), or is forcibly released by a reset by HW (hardware).

[0004]

Here, for example, the application 7 operating on the host computer 1 is H
Considering the case where the logical disk 13 is occupied and used via the BA 5, the interface cable 31, and the controller 11 ', the following problems occur.

[0005] The first problem is that the function of the path redundancy driver 3 'becomes meaningless in the following cases. The path redundancy driver 3 ′ is configured so that the application 7 operating on the host computer 1
Receives from the driver 4 the execution result of making an I / O request for, and determines normal termination or abnormal termination. At this time, it is assumed that the termination is determined to be abnormal, and that the cause is determined to be a failure (failure) in a component of the path (the HBA 5, the interface cable 31, or the controller 11 '). As a result, the HBA 6, the interface cable 32, and the
Then, a retry process of the abnormally terminated I / O is attempted via the controller 12 '. However, since the logical disk 13 is occupied by another initiator (HBA 5), reading / writing cannot be performed, and as a result, the I / O request of the application 7 ends abnormally. Therefore, the path redundancy driver 3 'cannot achieve its intended purpose.

The second problem is that when the occupation state is released by forcibly resetting by the hardware, the controller 1
One or more I / Os during processing received from the host computer 1 by initializing 1 ′ and 12 ′
Since all requests are discarded, unnecessary retry processing occurs on the host computer 1 side. Further, when the bus (host interface) is reset, all the devices (single devices 20, 21) connected to the bus are also initialized, so that a greater burden (retry) is imposed on the host computer 1 side. Process).

[0007] Considering the case where the host computer 1 occupies an arbitrary logical disk 13 to 15 for the purpose of protecting data consistency on the logical disks 13 to 15, the following problem occurs. I do.

A third problem is that temporarily releasing the occupation state of a logical disk from a certain host computer to a released state permits access from a host computer that is not intended at all, and therefore the logical disk is not allowed to be accessed. Data may be destroyed.

[0009]

SUMMARY OF THE INVENTION It is an object of the present invention to provide a redundant path control device and a redundant path control method which can access an already reserved logical disk by using an alternative path.

[0010]

SUMMARY OF THE INVENTION A redundant path control device (or redundant path control method) according to the present invention uses a substitute path including an initiator for a logical disk when an I / O access path fails. A redundant path control means for resetting the logical disk to the reserve state by the initiator of the alternative path when the retry processing ends abnormally because the logical disk is reserved by another initiator. (Or redundant path control step).

It is assumed that retry processing is executed on a logical disk using an alternative path, and the logical disk has already been reserved by another initiator, so that the retry processing ends abnormally. Then, the redundant path control means (or the redundant path control step) resets the logical disk to the reserved state by the initiator of the alternative path. As a result, for that logical disk,
Access can be made using an alternative path.

The redundant path control means (or redundant path control step) issues a forced reserve command from the initiator of the alternative path when the retry processing ends abnormally because the logical disk is reserved by another initiator. The first control means (or the first control step), and the second control means (or the second control means) for resetting the logical disk to the reserved state by the initiator of the alternative path when the forced reserve command is issued. Step) (claims 2 and 6).

Further, a plurality of logical disks may collectively constitute a disk array device (claims 3 and 7), or the initiator may be an HBA (claims 4 and 8).

[0014]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of a redundant path control device according to the present invention will be described with reference to the drawings. The redundant path control method according to the present invention is used in the redundant path control device according to the present invention. Therefore, by describing the present embodiment, one embodiment of the redundant path control method according to the present invention is also described.

FIG. 1 is a block diagram showing an embodiment of a redundant path control device according to the present invention. Hereinafter, description will be made based on this drawing. The first means and the second means in the claims correspond to the path redundancy driver and the controller in the present embodiment, respectively.

The HBAs 5 and 6 of the host computer 1 are:
They are connected to the controllers 11 and 12 of the disk array device 10 via interface cables 31 and 32, respectively. The host computer 1 executes I / O to the logical disks 13 to 15 in the disk array device 10. The driver 4 controls the HBAs 5 and 6 and controls the I / O
Perform processing.

The path redundancy driver 3 operates as follows. The I / O received from the file system 2 is
Deliver to driver 4. An I / O execution result for one of the logical disks 13 to 15 in the disk array device 10 is received from the driver 4 via the HBAs 5 and 6, and a normal end or an abnormal end is determined. If the cause of the abnormal termination is determined to be a failure (failure) in a component of the path (HBA 5, 6, interface cable 31, 32, controller 11, 12, etc.), an alternative path is used.
The retry processing of the I / O that ended abnormally is performed.

The controller 1 of the disk array device 10
1 and 12 are connected to the respective logical disks 13 to 15 via internal buses 16 and 17, respectively. Each of the logical disks 13 to 15 can be sent from either of the controllers 11 and 12.
Can be accessed.

For example, when the retry process ends abnormally because the logical disk 13 is reserved by another initiator 5, the path redundancy driver 3 issues a forced reserve command from the initiator 6 of the alternative path. When the forced reserve command is issued, the controller 12 resets the logical disk 13 to the reserved state by the initiator 6 of the alternative path.

FIG. 2 is a flowchart showing a part of the process of processing the I / O command received from the host computer 1, and these processes are executed by the controllers 11 and 12 of the disk array device 10. FIG. 3 shows the driver 4
A normal termination or an abnormal termination is determined based on the I / O execution result received from the server, and the cause of the abnormal termination is determined by a component of the path (HBAs 5, 6, interface cables 31, 3).
2, failure in the controllers 11, 12, etc.)
If it is determined that the abnormally terminated I
This is a flow showing a part of the process of performing the / O retry process, and these processes are performed by the path redundancy driver 3. Hereinafter, the operation of the redundant path control device according to the present embodiment will be described with reference to FIGS.

The data (write I / O) written to the disk array device 10 by the application 7 operating on the host computer 1 includes the application 7, the file system 2, the path redundancy driver 3, the driver 4, the HBA 5, and the interface cable 31. To the controller 11 via the designated logical disk 1
It is written to any of 3 to 15.

Data (read I / O) read from the disk array device 10 by the application 7 operating on the host computer 1 is transmitted from one of the designated logical disks 13 to 15 to the controller 11,
It reaches HBA5 via interface cable 31,
It reaches the application 7 via the driver 4, the path redundancy driver 3, and the file system 2.

Each I / O by the host computer 1
It is general that the execution result of O is determined by each layer of the HBA 5, the driver 4, the file system 2, and the application 7, and some processing is performed as needed. Here, the path redundancy driver 3
Determines whether the I / O execution result received from the driver 4 is normal termination or abnormal termination, and determines whether the cause of the abnormal termination is a path component (HBA, interface cable,
If it is determined that a failure (failure) has occurred in the controller or the like, retry processing of the abnormally terminated I / O is performed using the alternative path.

Next, a state where the application 7 has reserved the logical disk 13 will be described.

A reserve command is a command for exclusively occupying a logical disk specified by a specific initiator (HBA). For example, when the logical disk 13 is designated from the HBA 5 via the controller 11 and reserved, the I / O (read or write) to the logical disk 13 from the HBA 5 via the controller 11 is performed unless a problem such as a failure occurs. Terminates normally.
However, the I / O (read or write) issued from the HBA 6 to the logical disk 13 via the controller 12 is “Reservation Conflict”.
Abnormal termination with error message "t".

As can be seen from the above, the path redundancy driver 3 cannot perform its function well for I / O to the logical disk 13 occupied by the reserve command.

A method for solving this problem will be described with reference to FIGS. 2 and 3.

FIG. 2 is a flowchart showing a part of the process of processing an I / O command received from the host computer 1 and executed by the controllers 11 and 12 of the disk array device 10. In order to solve this problem, a forced reserve means is provided in the disk array device 10.

First, it is determined whether or not a command received from the host computer 1 can be executed correctly (S101). If the command cannot be executed correctly, the process proceeds to abnormal termination processing (S11).
1). If the command can be correctly executed, it is determined whether the command is an existing command or a newly provided forced reserve command (S102). If the command is a forced reserve command, the flag is cleared (S103); otherwise, the process proceeds to the existing command decoding process (S1).
12).

Subsequently, it is determined whether or not the specified logical disk has already been reserved (S104). If the reservation has not been made, the reserved state is set by the initiator that has issued the forced reserve command (S10).
7). If the reserve has already been made, it is determined whether or not the reserve is reserved by an initiator different from the initiator that issued the forced reserve command (S1).
05). If it is a reserve from the initiator that has issued the forced reserve command, the process proceeds to the end processing (S11).
3). If the reservation was made by an initiator different from the initiator that issued the forced reserve command, a flag is set (S106), and the state is set to the reserve state by the initiator that issued the forced reserve command (S107).

Subsequently, the flag is confirmed (S10).
8) If the flag has not been set, the process proceeds to the end process (S110). If the flag is set, it is reserved by another initiator, so that the reserved state is released, the used flag is cleared (S109), and the process proceeds to the end processing (S11).
0).

FIG. 3 is a flowchart showing a part of the retry process performed by the path redundancy driver 3 and using the alternative path.

First, the path redundancy driver 3 performs I / O for the logical disks 1 to 15 in the disk array device 10.
The execution result of O is received from the driver 4, and a normal end or an abnormal end is determined. If the cause of the abnormal termination is determined to be a failure (failure) in a path component (HBA, interface cable, controller, etc.), retry processing of the abnormally terminated I / O is performed using an alternative path (S201). ). Subsequently, the retry result is determined (S
202) If there is no abnormality, the process proceeds to the normal end process (S209).

If there is an abnormality, it is determined whether or not the abnormality is caused by a logical disk reserved by another initiator (S203). In the case of an abnormality caused by another, the process shifts to an abnormal end process (S210). On the other hand, if the cause of the abnormality is a logical disk reserved by another initiator, a forced reserve command is executed for the same path (S204).

Subsequently, the result is determined (S20).
5). If the forced reserve command is not terminated normally, the process proceeds to abnormal termination processing (S211). If the forced reserve command ends normally, the occupation of the logical disk has been changed to this initiator,
Then, the I / O which ended abnormally is retried on the same path again (S206). Subsequently, the result of step 206 is determined (S207). If the retry is successful, the process proceeds to a normal end process (S208).

As described above, an I / O path redundancy system for a reserved logical disk is realized.

It is needless to say that the present invention is not limited to the above embodiment. For example, the following embodiment can be adopted.

The number of the HBAs 5 and 6 is limited by the type of the OS, the driver 4 or the HW of the host computer 1 and the like, and there is no limitation on the path redundancy driver 3. The number of controllers 11 and 12 and the number of ports for connecting the controllers 11 and 12 to the host computer 1 and the like via the interface cables 31 and 32 are not limited. Although the HBAs 5 and 6 and the controllers 11 and 12 are directly connected by the interface cables 31 and 32, a hub or a switch or the like may be interposed between them.

The number of disk array devices 10 connected to the host computer 1 is not limited. The number of host computers 1 connected to the disk array device 10 is not limited. Logical disks 13-in disk array device 10
There is no limit on the number of 14. The present invention relates to a disk array device 1
It is not limited to only 0.

[0040]

According to the redundant path control device and method according to the present invention, when the retry processing ends abnormally because the logical disk has already been reserved by another initiator, the redundant path is set to the reserved state by the initiator of the alternative path. By resetting the logical disk, the logical disk can be accessed using an alternative path. In other words, when a failure (failure) occurs in a component (HBA, interface cable, controller, etc.) of the path, even if there is an application that occupies the logical disk and is used, the replacement is performed so as not to affect the operation of the application. Retry by pass becomes possible.

Further, since the occupancy is not forcibly released by the reset by the hardware, the occurrence of unnecessary retry processing on the host computer side can be suppressed.

Further, since the occupation state of the logical disk is not released even temporarily, there is no opportunity to permit access from a host computer which is not intended at all, so that the danger of destroying data in the logical disk can be avoided. .

[Brief description of the drawings]

FIG. 1 is a block diagram showing an embodiment of a redundant path control device according to the present invention.

FIG. 2 is a flowchart illustrating an example of an operation of a controller in the redundant path control device of FIG. 1;

FIG. 3 is a flowchart illustrating an example of an operation of a path redundancy driver in the redundant path control device of FIG. 1;

FIG. 4 is a block diagram showing a conventional redundant path control device.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Host computer 2 File system 3 Path redundancy driver 4 Driver 5, 6 HBA 7 Application 30-33 Interface cable 10 Disk array device 11, 12 Controller 13-15 Logical disk 16, 17 Internal bus 20, 21 Single device

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 5B014 EB04 FA04 GA15 GD22 GD32 HA11 5B065 BA01 CA30 EA05 EA12 5B083 AA05 BB03 CC01 CD06 EE08 EF14

Claims (8)

[Claims] 1. A redundant path control device for performing a retry process on a logical disk using an alternative path including an initiator when a failure occurs in an I / O access path, wherein the logical disk is reserved by another initiator. A redundant path control unit that resets the logical disk to a reserved state by the initiator of the alternative path when the retry processing ends abnormally because of the error. 2. The method according to claim 1, wherein the redundant path control unit issues a forced reserve command from the initiator of the alternative path when the retry processing ends abnormally because the logical disk is reserved by another initiator. 2. The redundant path control device according to claim 1, further comprising: a second control unit configured to reset the logical disk to a reserved state by an initiator of the alternative path when the forced reserve command is issued. 3. . 3. The redundant path control device according to claim 1, wherein a plurality of said logical disks form a disk array device. 4. The method according to claim 1, wherein the initiator is an HBA (Host).
4. The redundant path control device according to claim 1, wherein the redundant path control device is a Bus Adapter. 5. A redundant path control method for performing a retry process on a logical disk using an alternative path including an initiator when a failure occurs in an I / O access path, wherein the logical disk is reserved by another initiator. A redundant path control step of resetting the logical disk to a reserved state by an initiator of the alternative path when the retry processing ends abnormally because of the error. 6. The redundant path control step, wherein, if the retry processing ends abnormally because the logical disk is reserved by another initiator, a first command is issued from the initiator of the alternative path. 6. The redundant path control method according to claim 5, further comprising: a control step of: resetting the logical disk to a reserved state by an initiator of the alternative path when the forced reserve command is issued. . 7. The redundant path control method according to claim 5, wherein a plurality of the logical disks are collected to form a disk array device. 8. The method according to claim 1, wherein the initiator is an HBA (Host B).
8. The redundant path control method according to claim 5, 6 or 7, wherein the redundant path control method is a USB adapter.