JPH10254639A - Storage device system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain high availability by giving redundancy to a storage medium, an R/W device, a storehouse, and a robot respectively, managing fault states of the respective devices independently, and performing the read/write process of the storage system as much as possible. SOLUTION: A control unit 1350 grasps the fault state of a slot corresponding to a slot parity group and the fault state of a physical storage medium 1311 stored in the slot and judges whether or not a mounting process and an R/W process for the physical storage medium corresponding to the slot can be performed. The control unit 1305 grasps the fault state of the storehouse 1306 including the slot corresponding to the slot parity group by referring to storehouse state information and checks whether or not the physical storage medium 1311 can be taken out of the storehouse 1306. The control unit 1305 checks whether or not the stored physical storage medium 1311 can be carried to and from the R/W device 1304 by referring to robot constitution/state information.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a highly available storage system for portable storage media. In particular, the present invention relates to a storage system having redundancy in each component to improve availability.

[0002]

2. Description of the Related Art As a known example closest to the invention, the following Patterson article is known.

[0003] A. C. M. Sigmod Conference Proceedings, 1988, June, page 109.
−116 (D. Patterson, et al: A Case for Redundant A
rraysof Inexpensive Disks (RAID), ACM SIGMOD confere
nce proceeding, Chicago, IL, June 1-3, 1988, pp.109-11
6) Patterson's paper discloses a technique related to data arrangement on a disk array.

[0004] The disk array is a mechanism for realizing high performance and high reliability of the disk system. In a disk array, in order to improve performance, physically a plurality of disk devices appear as one disk device to a processing device. On the other hand, for higher reliability, when a failure occurs in a disk device storing data, redundant data for recovering data is stored in another disk device.

[0005] Usually, data which is a read / write unit of a disk device is called a record.
Proposed several record placement methods. However, when a disk array is used, a record which is a read / write unit viewed from the processing device may have a different data length from a record actually recorded on the disk device. Hereinafter, the former is called a logical record and the latter is called a physical record. Hereinafter, some record arrangement methods proposed in the Patterson's paper will be described.

A first arrangement method is an arrangement method in which a logical record, that is, a record viewed from the processing device side, is divided into m physical records (m ≧ 1) on a disk device and stored. Hereinafter, this arrangement method is referred to as a division arrangement method. When the divided arrangement is used, one logical record can be transferred to and from m disk devices, so that the same effect as apparently increasing the data transfer speed by m times can be obtained. Next, a method of creating redundant data in the divided arrangement will be described. In the divided arrangement, n (n ≧ 1) are assigned to m physical records obtained by dividing a logical record.
Of redundant data is created, and each is stored in the disk device as one physical record (there are n in total). Hereinafter, a physical record that stores data that is directly read / written by the processing device is called a data record, and a physical record that stores redundant data is called a parity record. A group including m data records and n parity records is called a parity group. Normally, if the number of parity records in a parity group is n, even if a failure occurs in up to n disk devices, data in the parity group can be recovered. Second
In the arrangement method, a logical record, which is a read / write unit as viewed from the processing device, is converted into one physical record, that is,
This is an arrangement method in which one data record is stored on a disk device. Hereinafter, this is referred to as a non-divided arrangement. Therefore, a logical record is equivalent to a data record. (Since a data record or a parity record is assigned to each physical record, a physical record and a logical record are not necessarily equivalent. That is, one logical record is one physical record, but one physical record is (It is not necessarily one logical record but may be a parity record.) The feature of the non-divided arrangement is that the read / write processing can be executed for each disk device constituting the disk array. . (If the split arrangement method is adopted, it is necessary to occupy a plurality of disk devices for read / write.) Therefore, if the non-divided arrangement is adopted, the multiplicity of read / write processing that can be executed in the disk array is improved. And the performance can be improved.
Even in the non-divided arrangement, n parity records are created from m data records and stored in the disk device.
However, in the case of the split arrangement, a set of data records in the parity group forms one logical record as viewed from the processing device, whereas in the non-split arrangement, each of the data records is viewed from the processing device. It becomes a completely independent logical record.

[0007] In computer systems, magnetic tapes and magnetic tapes are often used as storage devices other than disk devices.
There are optical storage devices and the like. Particularly recently, DVD (Digital)
tal Video Disk) is attracting attention. These storage devices are characterized by a storage medium and R / W
(Read / Write) device is separated, a storage medium is loaded into an arbitrary R / W device, and data on the storage medium is read / written. Generally, these media are referred to as portable media. In a large-scale computer system, a library is introduced to easily manage a very large number of portable media. The library includes, in addition to the storage medium and the R / W device, a storage for storing a large number of storage media, a robot for transferring the storage medium between the storage and the R / W device, and the like. .

[0008] Since the data handled by the computer system is becoming increasingly large-scale, it is necessary to improve its availability.
Is also very high. Therefore, even in the storage device system constituted by the portable medium as described above, the Pattern
It is effective to achieve high availability by applying the concept proposed in the son's paper.

As a technique in which such a concept is applied to a portable medium, Comdex 96: DVD application is available.
Alan E. Bell (IBM Research Division): DVD
Applications, COMDEX 96, Nov. 20, 1996). In this document, an RA having redundancy is obtained by combining a plurality of ordinary libraries including DVDs, R / W devices, robots, and the like.
IL (Redundant Arrays of Inexpensive Libralies)
Has been proposed.

[0010]

[0006] RAIL is considered to have no redundancy because one library that is a component of the RAIL is an ordinary library. A feature of the RAIL concept is that it adds redundancy by adding another library. That is, the unit of redundancy is a library.

[0011] Further, since RAIL is simply arranged a plurality of libraries, it is considered that each library is configured independently. That is, a robot in one library cannot transport a storage medium of another library, and cannot load a storage medium into an R / W device of another library.

For example, suppose that a robot in a library has failed. With this alone, normal read / write processing can be performed using the remaining libraries. However, if one storage medium in the remaining library fails, the storage medium in the failed library described above is required to restore the contents of the failed storage medium. However, this storage medium is referred to as R / W
It cannot be loaded into the device. Therefore, the data cannot be restored, and the user will see the failure.

An object of the present invention is to provide a technology for further improving the availability in a storage system based on a portable medium as compared with the above-mentioned conventional technology.

[0014]

The following is a description of how to achieve the object of the present invention for the above-mentioned problems.

As described above, a feature of the RAIL concept is that redundancy is provided by adding another library. That is, the unit of redundancy is a library.

On the other hand, in the present invention, each device, storage medium, R / W device, storage, and robot which are components of one library are considered to have independent redundancy. Then, whether the state is normal or faulty is managed. In addition, the robot can transfer R
/ W Flexibility in the range of equipment and storage.

[0017] This makes it possible to effectively use a device in a normal state among the devices, thereby realizing extremely high availability. For example, in the present invention, even in the following situation,
A data read / write function can be provided without making the user aware of the failure. That is, if one storage medium in the remaining library fails in a situation where a certain robot has failed, a redundant group including the failed storage medium is used by using a non-failing robot. The remaining storage media to which the storage media belong can be loaded into the R / W device, and the process of restoring the data of the failed storage media can be executed.

[0018]

FIG. 2 shows the configuration of a computer system to which the present invention is applied. The computer system includes a processing device 1300, a control device 1305, and two or more R /
W device 1304, two or more media storage warehouses 130
6, consisting of two or more robots 1307. The processing device 1300 may include a CPU 1301, a main storage 1302, and a channel 1303 in some cases. The control device 1305 executes a transfer process between the processing device 1300 and the disk device 1304 according to a read / write request from the processing device 1300. The control device buffer 1310 is a buffer that temporarily stores data read and written by the control device 1305.

The storage warehouse 1306 stores a plurality of physical storage media 1311 storing data. The robot 1307 includes a storage warehouse 1306 and an R / W device 1304.
In between, the physical storage medium 1311 is carried. The R / W device 1304 reads and writes the physical storage medium 1311 set by the robot 1307.

FIG. 3 shows the configuration of another computer system to which the present invention is applied. The difference from the configuration shown in FIG. 2 is that control device 1305 includes cache memory 1308, directory 1309, nonvolatile memory 1400, and nonvolatile memory management information 1401. Cache memory (hereinafter simply referred to as cache) 1308
Is the physical storage medium 1 set in the R / W device 1304
Part of the data 311 is stored. Directory 130
9 stores the management information of the cache 1308. The non-volatile memory 1400 is a non-volatile medium and, like the cache 1308, stores a part of data of the physical storage medium 1311 set in the R / W device 1304.
The nonvolatile memory management information 1401 is also a nonvolatile medium, and stores management information of the nonvolatile memory 1400. In this case, the control device 1305 synchronizes with the read / write request from the processing device 1300 asynchronously with the R / W device 130.
4 and the cache 1308 perform a read / write operation. However, as shown in FIG.
The present invention is also effective in a configuration in which two or more directors 1312 are included in 305, and each director 1312 receives a read / write request from the processing device 1300 and executes a read / write operation.

Normally, a unit of data read / written by the processing device 1300 to / from a disk device is called a record. However, in the present invention, the record viewed from the processing device 1300 and the record stored on the physical storage medium 1311 may differ depending on the record arrangement of the disk array. Hereinafter, a data recording format when a disk array is applied will be described.

Next, the recording format of the physical storage medium 1311 in this embodiment will be described with reference to FIGS. The logical storage medium 400 is a single storage medium viewed from the processing device 1300. On the other hand, the physical storage medium 1311 is a single storage medium, as described above, and is a storage unit of the storage warehouse 1306, a robot 1307.
And a set unit of the R / W device 1304.
In the configuration of FIG. 4, m + n physical storage media 1311 are 1
One logical storage medium 400 is obtained. As shown in FIG. 5, a logical record 401 is a record read / written from the processing device 1300, that is, a record of the logical storage medium 400. On the other hand, as shown in FIG. 6, a unit read / written between the R / W device 1304 and the control device 1305, that is, a unit recorded on the physical storage medium 1311 is called a physical record 1502. In the present invention, there are two types of physical records 1502 stored on the physical storage medium 1311: a data record 1500 and a parity record 1501. The data record 1500 is a physical record 1502 that stores the contents of the logical record 401. On the other hand, the parity record 1501 indicates that the physical storage medium 1311 has failed,
When the content of the data record 1501 is lost, this is a record used for processing to recover the lost content. In this case, when the value of the data record 1500 is changed, the content of the parity record 1501 needs to be changed correspondingly.

The storage medium parity group 1610 in this embodiment shown in FIG. 6 will be described. In the configuration shown in FIG. 6, the storage medium parity group 1610
It corresponds to m + n physical storage media 1311 corresponding to one logical storage medium 400.

Next, the record parity group 1600
Will be described. One set of storage medium parity group 1
The corresponding data records 1500 are stored in the m physical storage media 1311 constituting the 610. From these m data records 1500, n parity records 1501 are created and stored in the corresponding n physical storage media 1311 respectively. Accordingly, in FIG. 6, a record parity group 1600 is composed of m data records 1500 and n parity records 1501. Of course, a plurality of records can be stored on one storage medium parity group 1610.
It is natural that the parity group 1600 is stored. In general, n parity records 1501
In the record parity group 1600 including
Even if n physical storage media 1304 out of the m + n physical storage media in which the physical records 1502 in the record parity group 1600 are stored, the record is lost.
The contents of all physical records 1502 in the parity group 1600 can be recovered. As described above, high reliability of the physical storage medium 1311 can be realized. Of course, each physical storage medium 1311 includes a plurality of physical records 1502, and one parity group storage medium 1610 has a plurality of parity groups 1600.

As shown in FIG. 8A, a plurality of logical storage media 400 may correspond to one set of parity group storage media 1610. It should be noted that the present invention relates to FIG.
As shown in (1), a plurality of parity group storage media may correspond to one logical storage medium 400.

FIG. 9 shows an R / W device parity group 90.
0 and a logical R / W device 901 are shown. The R / W device parity group 900 is composed of m + n R / W devices 1304, and is loaded with a set of parity group storage media 1610. In the present embodiment, the control device 1305 includes 1
It is assumed that more than one set of R / W device parity groups 900 are connected. On the other hand, the logical R / W device 901 is a logical device that executes R / W processing as viewed from the processing device 1300, and loads the logical storage medium 400. FIG.
As shown in (a), when one storage medium parity group 1610 corresponds to one logical storage medium 400, or one storage medium parity group 161
When 0 corresponds to a plurality of logical storage media 400, R /
One-to-one correspondence with the W device parity group 900. On the other hand, as shown in FIG. 9B, when the plurality of storage medium parity groups 1610 correspond to one logical storage medium 400, the logical R / W device 901 becomes the plurality of R / W device parity groups 900. Corresponding to

FIG. 10 shows the configuration of the storage warehouse 1306. The storage warehouse 1306 has a common part 1001 and a plurality of slots 1000. The common unit 1001 includes common resources such as a power supply. Obstacle of common part 1001 is storage warehouse 13
06 will be an obstacle. The slot 1000 is a unit for storing one physical storage medium 1311. Slot 1
000 fail independently.

FIG. 11 shows a slot parity group 11
00 and the logical slot 1101 are shown. The slot parity group 1100 is a set of m + n slots 1000 containing m + n physical media 1311 belonging to one storage medium parity group 1610. In the configuration shown in FIG. 11, the slots 1000 belonging to the slot parity group 1100 are stored in different storage warehouses 13 respectively.
06 is a slot 1000. However, of course, the present invention provides one slot parity group 11
It is effective even if two or more slots 1000 belonging to 00 are included in the same storage warehouse 1306. The logical slot 1101 is a logical storage unit that stores the logical storage medium 400 as viewed from the processing device 1300. The storage medium parity group 1610 is used for one logical storage medium 400.
In this case, as shown in FIG. 11A, the logical slot 1101 is a slot parity group 110.
It corresponds to 0 and 1 to 1. On the other hand, the storage medium parity group
When the group 1610 corresponds to a plurality of logical storage media 400, the slot parity group 1100 corresponds to a plurality of logical slots 1101, as shown in FIG. Further, as shown in FIG. 11C, when a plurality of storage medium parity groups 1610 correspond to one logical storage medium 400, the logical slot 1101 corresponds to a plurality of slot parity groups 1100.

In this embodiment, a case where the storage medium parity group 1610 corresponds to one logical storage medium 400 will be described. Of course, the present invention is also effective when the storage medium parity group 1610 corresponds to a plurality of logical storage media 400.

FIG. 1 shows the outline of the present invention. As information related to the present invention, the control device 1305 stores slot parity group configuration / status information 100, storage warehouse status information 101, and R / W device parity group in the control device buffer 1312, the directory 1309, the nonvolatile memory management information 1401, and the like. -Configuration / state information 102 and robot configuration / state information 103.

The slot parity group configuration / state information 100 includes an identifier of the slot 1000 constituting the slot parity group 1100, a failure status, a storage warehouse 1306 including the slot 1000, and physical storage stored in the slot 1000. It includes information such as an identifier of the medium 1311 and a failure status.

The storage warehouse state information 101 is stored in the control unit 13
5 shows fault information of each storage warehouse 1306 connected to the storage warehouse 1.

The R / W device parity group configuration / status information 102 indicates an identifier of the R / W device 1304 constituting the R / W device parity group 900 and a failure state.

The robot configuration / state information 103 indicates failure information of each robot 1307 connected to the control device 1305, and the storage warehouse 1306 and the R / W device 1304 to which the robot 1307 can transfer. As described above, the storage warehouse 1306 that can be transported by the robot 1307,
By making the range of the R / W device 1304 flexible,
Improve availability. That is, the robot 1307
Even if one fails, it is possible to prevent the appearance of the storage warehouse 1306 and the R / W device 1305 in which the physical storage medium 1311 cannot be transported.

The main functions of the control unit 1305 are a mount processing execution unit 110, an R / W processing execution unit 111, a demount processing execution unit 112, and a fault state management processing execution unit 113.

The mount processing execution unit 110 is a processing unit 1
The logical storage medium 400 is loaded in the logical R / W device 901 according to the request of 300.

The R / W processing execution unit 111
In response to the request of 00, the R / W processing of the logical storage medium 400 loaded in the logical R / W device 901 is executed. The demount processing execution unit 112 removes the logical storage medium 400 loaded in the logical R / W device 901 according to a request from the processing device 1300.

When a failure occurs in each device, the failure state management processing execution unit 113 executes the slot parity group configuration /
The status information 100, the storage warehouse status information 101, and the robot configuration / status information 102 are rewritten.

The outline of the mount processing execution unit 110 will be described. First, in step 120, the control device 1305
By analyzing the received mount request, the requested logical storage slot 1101 is identified as a slot parity group 1
Calculate whether it corresponds to 100. In this embodiment, the logical slot 1101 and the slot parity group 1100
Since they correspond one-to-one, they can be easily recognized. Even when there is no one-to-one correspondence, it can be recognized without any problem by having a correspondence table or the like. In step 121, the control device 1
Reference numeral 305 denotes a failure status of the slot 1000 corresponding to the slot parity group 1100;
The failure status of the physical storage medium 1311 stored in the logical slot 1101 is grasped, and it is determined whether the mounting processing and the R / W processing of the logical storage medium 400 corresponding to the logical slot 1101 can be executed.

At step 122, the controller 1305
Refers to the storage warehouse status information 101, grasps the failure status of the storage warehouse 1306 including the slot 1000 corresponding to the slot parity group 1100, and is it possible to remove the physical storage medium 1311 from the storage warehouse 1306? Check.

In step 123, the controller 1305
Is the logical R / W device 9 specified by the processing device 1300
The R / W device parity group 900 corresponding to 01 is calculated. In this embodiment, the logical R / W devices 901 and R / W
Since the W device parity group 900 has a one-to-one correspondence, it can be easily recognized. Even when there is no one-to-one correspondence, it can be recognized without any problem by having a correspondence table or the like.
In step 124, the control device 1305 checks the R / W
Referring to the R / W device parity group configuration / status information 102 corresponding to the device parity group 900, the processing device 1300 or the designated R / W device parity group 90
The failure status of the R / W device 1304 constituting 0 is checked, and it is checked whether the R / W process can be executed using the specified logical R / W device 901.

In step 125, the controller 1305
Is the physical storage medium 1311 stored in the slot 1000 corresponding to the designated slot parity group 1100 with reference to the robot configuration / state information 102.
Is checked with the R / W device 1304 constituting the designated R / W device parity group 900.

In step 126, the control device 1305
This transport processing is executed. If the transport process and the R / W process cannot be performed due to the failure status of each device, the processing device 1300
Report a problem to.

As described above, according to the present invention, since the failure status of each device is independently grasped, the device which does not cause a failure is utilized to the utmost, and the transport processing and the R / R of data are performed.
Since W processing can be performed, availability can be improved. Further, as already mentioned, the robot 1307
It is a major feature that the availability is improved by giving flexibility to the range of the storage warehouse 1306 and the R / W device 1304 that can transport the data.

FIG. 12 shows the slot parity group configuration / state information 100. The slot parity group configuration / state information 100 includes a slot parity group 11
It is information that exists in 00 units. Storage warehouse identifier 120
0 is information indicating which storage warehouse 1306 contains the slot 1000 belonging to the slot parity group 1100. The slot number 1201 is the slot 10 belonging to the slot parity group 1100.
00 in the storage warehouse 1306. The slot failure status 1202 indicates a failure status of the slot 1000. Specifically, whether the physical storage medium 1311 can be taken out of the slot 1000 by using the robot 1306 or the physical storage medium
Indicates whether can be stored.

The physical storage medium identifier 1203 is an identifier of the physical storage medium 1311 stored in the slot 1000. The physical storage medium fault information 1204 is fault information of the physical storage medium 1311 stored in the slot 1000. Specifically, the physical storage medium 1311
Shows whether data can be read and written. Above 1200
Since the information shown in -1204 is information in units of 1000 slots, one slot parity group configuration /
There are m + n items in the state information 100.

FIG. 13 shows the storage warehouse state information 101. The storage warehouse state information 101 exists for each storage warehouse 1306 unit. The storage warehouse state information 201 indicates a failure state of the corresponding storage warehouse 1306. Specifically, this is a case where a failure occurs in the common unit 1001 of the storage warehouse 1306. In addition, a certain number of slots 1
If 000 fails, the entire storage warehouse 1306 may be treated as a failure.

FIG. 14 shows the configuration of the R / W device parity group configuration / status information 102. The R / W device parity group configuration / status information 102 is information that exists for each R / W device parity group 900. The R / W device identifier 210 corresponds to the R / W device parity group 90.
The identifier of the R / W device 1304 belonging to “0”. R / W
The device failure status 211 indicates a failure status of the R / W device 1304. Specifically, it indicates whether the physical storage medium 1311 is loaded in the R / W device 1304 and whether the R / W process can be executed. Since the information indicated by 210 and 211 is information for each R / W device 1304, there are m + n pieces of information in one R / W device parity group configuration / state information 100.

FIG. 15 shows the robot configuration / state information 103.
Is information for each robot 1307. The robot failure information 220 indicates that the robot 1307 indicates that the physical storage medium 1
This is information indicating whether or not the transfer of 311 is possible.
The number 221 of connected storage warehouses is the number of storage warehouses 1306 connected to the robot 1306, specifically, the storage warehouse 130 from which the physical storage medium 1311 can be taken out and stored.
Represents the number 6. The number of connected R / W devices 222 is the number of R / W devices 1304 connected to the robot 1306, specifically, the number of R / Ws to which the physical storage medium 1311 can be loaded.
Represents the number of devices 1304. The values of the number of connected storage warehouses 221 and the number of connected R / W devices 222 may be different for each robot 1307. The connected storage warehouse identifier 223 indicates an identifier of the storage warehouse 1306 connected to the robot 1306. The connected R / W device identifier 224 indicates the identifier of the R / W device 1304 connected to the robot 1306. The number of connection storage warehouse identifiers 223 is set by the number defined by the number of connection storage warehouses 221. However, it is assumed that an area for setting the connection storage warehouse identifier 223 is prepared more. (Each robot 1
This is because the number of connected storage warehouses 1306 may be different depending on 306. Similarly, the number of connected R / W device identifiers 224 is set by the number defined by the number of connected R / W devices 222. However, it is assumed that an area for setting the connection R / W device identifier 224 is prepared more than that. (Because the number of connected R / W devices 1304 may be different depending on each robot 1306.) As described above, in the present invention, different robots 1307 use the same storage warehouse 1306 and the same R / W device. The connection storage warehouse identifier 22 set in each robot configuration / state information 103 in order to improve the availability by enabling the transfer processing to be performed between 1304
3. There is a common connection R / W device identifier 224.

Next, among the execution units in the control device 1305 shown in FIG. 1, the detailed flow of the mount processing execution unit 110 and the failure state management processing execution unit 113 related to the present invention will be described. Do.

FIG. 16 shows a processing flow of the mount processing execution unit 110. The processing device 1300 is a logical slot 1
101 and the logical R / W device 901 are specified, and a request is made to load the logical storage medium 400 in the specified logical slot 1101 into the specified logical R / W device 901.

In step 300, the control device 1305
Analyzes the received mount request and calculates which slot parity group 1100 the specified logical slot 1101 corresponds to. In the present embodiment, the logical slot 1101 and the slot parity group 110
Since 0 corresponds to one-to-one, it can be easily recognized. 1
Even when the correspondence is not one-to-one, it can be recognized without any problem by having a correspondence table or the like.

In step 301, the controller 1305
Is the slot parity group 1 obtained in step 300
Reference is made to the slot parity group configuration / status information 100 corresponding to 100. Specifically, referring to the slot fault status 1202, the fault status of the slot 1000 is grasped. Further, referring to the physical storage medium failure information 1204, the failure status of the physical storage medium 1311 stored in each slot 1000 is grasped, and the logical storage medium 400
The physical storage medium 1311 that can execute the mount processing and the R / W processing is determined. In step 302, the control device 1
A step 305 checks whether or not the mounting processing and the R / W processing of the m or more physical storage media 1311 can be executed. If the condition is not satisfied, an error report is sent to the processing device 1300. I do.

In step 304, the controller 1305
Is the slot parity group 1 obtained in step 300
The storage warehouse status information 201 is referred to in order to grasp the failure status of the storage warehouse 1306 including the slot 1000 corresponding to the storage warehouse 100. Further, it is checked whether or not a failure has occurred in the storage warehouse 1306 including the slot 1000 accommodating the physical storage medium 1311 determined to be executable in the mounting process and the R / W process in step 302. If there is, the mounting process and the R / W process of the physical storage medium 1311 corresponding to the storage warehouse 1306 cannot be executed. In step 305, the control device 1305
Checks whether mount processing and R / W processing of m or more physical storage media 1311 are still executable, and if the condition is not satisfied, proceeds to step 303 in order to report an error to the processing device 1300. Jump.

In step 305, the controller 1305
Calculates which R / W device parity group 900 the designated logical R / W device 901 corresponds to. In the present embodiment, since the logical R / W device 901 and the R / W device parity group 900 correspond one-to-one, they can be easily recognized. Even when there is no one-to-one correspondence, it can be recognized without any problem by having a correspondence table or the like.

In step 306, the controller 1305
First, the R / W device parity group 900 corresponding to the R / W device parity group 900 obtained in step 305 is recognized. With reference to the R / W device failure status 211 in the R / W device parity group configuration / status information 102, the R / W device 1304 belonging to the R / W device parity group 900 performs mount processing, The R / W device 1304 capable of executing the R / W process is grasped. In step 307, the control device 1305 checks whether or not the mounting process and the R / W process of the m or more R / W devices 1304 can be executed. If the conditions are not satisfied, an error report is sent to the processing device 1300. To do so, jump to step 303.

In the present invention, the storage medium parity group 1
Each physical storage medium 1311 belonging to 610
/ W Any R / W belonging to the device parity group 900
The device 1304 can be loaded. (Of course, there is a restriction that the robot 1307 can be transported.) This is because if a restriction is placed on the loadable R / W device 1304, availability in the event of a failure is reduced.

At step 308, the controller 1305
Refers to the robot configuration / state information 102, and executes m or more physical storage media 1311 capable of executing the mount processing and the R / W processing in step 305, and executes the mount processing and the R / W processing in step 307. The robot 1306 is actually connected to at least m possible R / W devices 1304.
The physical storage medium 1311 that can be transported / loaded is grasped.
In step 309, the control device 1305 checks whether there are m or more physical storage media 1311 that have been determined to be capable of carrying / loading.
At 00, the process jumps to step 303 to make an error report.

At step 310, the controller 1305
Executes a mount process of using the robot 1306 to transfer and load the physical storage medium 1311 determined to be transferable / loadable to the R / W device 1304. Step 31
In step 1, this completion report is made.

On the other hand, at step 303, the controller 13
05 reports to the processing device 1300 that the requested mount processing cannot be executed due to a failure.

FIG. 17 shows the fault state management processing execution unit 113.
Is a process executed when the management information of the control device 1305 is updated when a failure occurs in a device connected to the control device 1305.

Step 1700 is performed by the controller 1305
Analyzes the failed device. As a result, the process branches to each step.

Step 1701 is performed in the physical storage medium 131.
This is a process performed when a failure occurs in No. 1. Step 170
In 1, the controller 1305 sets the slot parity group
Storage medium identifier 120 in the configuration / status information 100
3, the physical storage medium fault information 1204 of the failed physical storage medium 1311 is updated to the fault state. Thereafter, the process ends.

Step 1702 is a process when a failure occurs in the slot 1000. In step 1702, the control device 1305 refers to the storage warehouse identifier 1200 and the slot number 1201 in the slot parity group configuration / state information 100, and
000 is updated to the failure state. Further, in step 1703, the control device 1305 refers to the slot parity group configuration / state information 100 and checks whether the number of failed slots 1000 in the storage warehouse 1306 including this slot 1000 has exceeded a certain number. . If not, the process ends. If it has exceeded, the process jumps to step 1704 to put the storage warehouse 1306 into a failure state.

Step 1704 is processing when a failure occurs in the storage warehouse 1306. In step 1704, the control device 1305 determines that the storage warehouse 13
The storage warehouse state information 101 corresponding to 06 is updated to the failure state. Thereafter, the process ends.

Step 1705 is for the R / W device 1304
This is the process when a failure has occurred. Step 1705
Then, the control device 1305 controls the R / W device parity group.
The R / W device failure status 211 corresponding to the failed R / W device 1304 is updated to the failure status with reference to the R / W device identifier 210 in the configuration / status information 102.

Step 1706 is processing when a failure occurs in the robot 1307. In step 1706, the control device 1305 determines that the failed robot 13
The robot failure information 220 corresponding to 07 is updated to the failure state. Thereafter, the process ends.

[0068]

A large-scale storage system data based on a portable medium is a recorded storage medium, an R / W device for reading and writing data, a storage for storing the storage medium, and a storage medium. Often, it is constituted by a group of devices including a robot or the like for transporting the robot. In the present invention, a storage medium, an R / W device,
Achieve high availability by providing redundancy in the storage warehouse and robot, and independently managing the failure state of each device, and executing read / write processing in the storage system as much as possible. .

[Brief description of the drawings]

FIG. 1 is a schematic diagram of the present invention.

FIG. 2 is a configuration diagram of a computer system to which the present invention is applied.

FIG. 3 is a configuration diagram of another computer system to which the present invention is applied.

FIG. 4 is a configuration diagram of a logical storage medium 400.

FIG. 5 is a relationship diagram of a logical record and a physical record.

FIG. 6 is a configuration diagram of a storage device parity group and a record parity group.

FIG. 7 is a configuration diagram when a plurality of directors exist.

FIG. 8 is a diagram showing the relationship between a logical storage device and a storage device parity group.

FIG. 9 is a configuration diagram of an R / W device parity group and a logical R / W device.

FIG. 10 is a configuration diagram of a storage warehouse.

FIG. 11 is a configuration diagram of a slot parity group and a logical slot.

FIG. 12 is a configuration diagram of slot parity group configuration / state information.

FIG. 13 is a configuration diagram of storage warehouse state information.

FIG. 14 is a configuration diagram of an R / W device parity group configuration / state information.

FIG. 15 is a configuration diagram of robot configuration / state information.

FIG. 16 is a processing flowchart of a mount processing execution unit.

FIG. 17 is a processing flowchart of a failure state management processing execution unit.

[Explanation of symbols]

100: slot parity group configuration / status information, 1
01: Storage warehouse status information, 102: R / W device parity group configuration / status information, 103: Robot configuration / status information, 110: Mount process execution unit, 111: R / W process execution unit, 112: Demount process execution Unit, 113: failure state management processing execution unit

Claims (1)

[Claims] 1. One or more sets of storage media groups each comprising m + n storage media, and one or more sets of record groups stored in respective storage media of said storage medium groups. The record group includes m data records (m ≧ 1) storing data to be accessed by a processing device and redundant data for recovering data stored in the data records. (N ≧ 1)
One or more storage warehouses each having a plurality of storage units for storing the storage medium, and loading the storage medium,
M + n or more read / write operations for executing a read / write operation
A light device, one or more robots for transporting the storage medium between the storage warehouse and the R / W device, the storage warehouse, the read / write device, and the robot according to a request from a processing device. A storage device system comprising: a control device that performs control; a failure status of the storage medium, a failure status of the storage unit, a failure status of the storage warehouse, a failure status of the robot, Means for managing the failure status of the read / write device, and whether the processing / transfer process of the storage medium group requested by the processing device to the read / write device or the read / write process is possible. It is determined whether or not the failure condition of the storage medium, the failure condition of the storage unit, the failure condition of the storage warehouse, the failure condition of the robot, and the failure condition of the read / write device. Storage system characterized by having steps.