US20060248302A1

US20060248302A1 - Storage unit, installation method thereof and installation program therefore

Info

Publication number: US20060248302A1
Application number: US11/476,704
Authority: US
Inventors: Yasutomo Yamamoto; Yoshiaki Eguchi; Ai Satoyama; Hiroshi Ohno
Original assignee: Individual
Current assignee: Individual
Priority date: 2003-01-16
Filing date: 2006-06-29
Publication date: 2006-11-02
Also published as: US20040143832A1; EP1439452A2; EP1439452A3; DE07000607T1; US7177991B2; US20050246491A1; JP2004220450A; EP1770502A3; EP1770502A2

Abstract

A new storage unit is installed such that installation costs are suppressed and functions of the new storage unit can be utilized sufficiently. An access right is changed such that the new storage unit (second storage unit) can access an existing first storage unit (S502). A logical device relating to a storage device of the first storage unit is assigned to a logical device of the second storage unit (S503). Path definition and device recognition in a host computer are performed such that the host computer can access the assigned logical device of the second storage unit (S504, 505). Input-output setting of the host computer is changed such that processing of an input-output from the host computer to the device of the first storage unit is requested to the second storage unit (S506).

Description

The present application is a continuation application of application Ser. No. 11/178,373, filed Jul. 12, 2005, which is a continuation of application Ser. No. 10/636,758, filed Aug. 8, 2003, the contents of which are incorporated herein by reference.

BACKGROUND OF THE INVENTION

1. Field of the Invention
The present invention relates to a storage unit that is installed newly into a computer system comprising a first storage unit and a host computer accessing the first storage unit, and an installation method thereof and an installation program therefor.
2. Related Art Statement
Recently, an amount of data treated by a computer is increasing by leaps, and accordingly storage capacity of a storage unit for storing data is increasing. As a result, costs of storage management in system management increase, and reduction of management costs becomes an important problem from the viewpoint of system operation.
When a new storage unit is installed into an existing computer system that comprises a host computer and a storage unit, two modes can be considered as a mode of installation, namely, a mode in which the old storage unit is used as ever, and the new storage unit is used together with the old storage unit, and a mode in which all the data on the old storage unit are migrated onto the new storage unit.
For example, as to the latter mode of installation, Japanese Patent Publication No. 10-508967 discloses a technique of migrating data of an old storage unit onto a new storage unit. According to the technique disclosed in the above document, data of a first device in the old storage unit are migrated onto a second device assigned to the new storage unit. Then, a host computer's access destination is changed from the existing first device to the new second device. An input-output request from the host computer to the existing first device is received by the new storage unit. With respect to a read request, a part whose migration is finished is read from the new second device, while a part that has not been migrated yet is read from the existing first device. Further, with respect to a write request, dual writing is performed toward both the first and second devices.
As described above, when a new storage unit is installed, it is possible to migrate data of a first device within an old storage unit to a second device within a new storage unit, without stopping input/output from/to a host computer.
However, in the case of the former mode of installation, where the new storage unit and the old storage unit are used side by side, there is a problem that, although generally the new storage unit has high function, high performance and high reliability in comparison with the old storage unit, it is impossible for data stored in the old storage unit to enjoy the merits of the new storage unit.
Further, in the case of the latter mode of installation, where all the data of the old storage unit are migrated onto the new storage unit, it is possible to enjoy the merits of the new storage unit by migrating the data stored in the old storage unit. However, there is a problem that, to migrate all the data of the old storage unit onto the new storage unit, the new storage unit must have more storage capacity than the old storage unit, and thus, the system installation cost is raised up.
Thus, as a compromise between them, it is possible to consider the following operation. Namely, the number of disk units mounted on a new storage unit is restrained to decrease initial investment, and the minimum data are migrated from an old storage unit to start system operation. At a stage in which a disk unit is added to the new storage unit, data is migrated from the old storage unit by an amount that the added disk unit allows. However, even by this compromise, data that can not be migrated because of storage capacity can not enjoy the merits of the new storage unit, similarly to the case where two storage units are used side by side.

SUMMARY OF THE INVENTION

An object of the present invention is to provide such a storage unit, an installation method thereof and an installation program therefor that can enjoy merits such as high function, high performance and high reliability of a new storage unit at the time of installation of the new storage unit, suppressing cost increase.
To attain the above object, the present invention follows the below-described procedures to install a new storage unit (referred to as a second storage unit) into a computer system comprising a host computer and an existing first storage unit, wherein the host computer and the first storage unit are connected through a first network such as SAN, LAN, or the like.
First, the new second storage unit is connected to the first network. Then, zoning setting of a switch existing in the first network and access right setting of the first storage unit are changed such that the second storage unit can access a storage device in the first storage unit. Next, a logical device (hereinafter, referred to as a first logical device) relating to the storage device of the first storage unit is assigned to a logical device (hereinafter, referred to as a second logical device) of the second storage unit. Namely, the first logical device of the first storage unit is associated with the second logical device of the second storage unit. Next, with respect to the second logical device, path definition and device recognition in the host computer are performed such that the host computer can recognize the second logical device of the second storage unit and can access the second logical device of the second storage unit.
Next, input-output setting of the host computer is changed such that processing of an input-output from the host computer to the storage device of the first storage unit is requested to the second storage unit. Here, the substance of the second logical device is the storage device in the first storage unit, and a storage device storing the data of the second logical device is not held in the second storage unit.
Favorably, the zoning setting of the switch existing in the first network and the access right setting of the first storage unit are changed such that direct access from the host computer to the storage device of the first storage unit is inhibited.
In the above-described state, when the second storage unit receives a read request from the host computer to the second logical device, then, the second storage unit converts the read request into a read request to the first logical device, and sends the converted request to the first storage unit. Receiving an input-output processing completion report from the first storage unit, the second storage unit sends the host computer a completion report relating to the input-output request to the second logical device.
Thus, in the above-described state, the second storage unit can process an input-output request to the storage device in the first storage unit. Accordingly, merits of the new storage unit, such as high performance, high reliability and high function, can be applied to the device in the existing first storage unit. For example, to the first logical device of the first storage unit, the second storage unit can apply a replicating function such as data replication and copy to a remote place, or access right control for each device.
Here, apparently the second logical device of the second storage unit is assigned to the first logical device of the first storage unit, and the host computer recognizes the first logical device of the first storage unit as the second logical device of the second storage unit. In this state, a physical device that becomes the substance of the second logical device is allocated from an unused storage space in the second storage unit, and a part or all of the data of the storage devices of the first storage unit are migrated. In the course of data migration, when a read request from the host computer to the second logical device relates to data that have not been migrated from the first logical device, then, this read request is sent to the first storage unit, as a read request to the first logical device. On the other hand, when this read request relates to data that have been migrated already, this read request is processed in the second storage unit, as a read request to the above-mentioned physical device as the subject of the second logical device. Further, with respect to a write request in the course of data migration, dual writing is performed toward the first logical device of the first storage unit and toward the physical device of the second storage unit. When the data migration from the first storage unit is finished, then setting is changed such that the physical device of the second storage unit is seen as the second logical device.
Thereafter, each time when a new storage device is added to the second storage unit, data of the first storage unit are migrated stepwise.
When the second storage unit is installed according to the above-described method, then, also with respect to data that are actually stored in the existing first storage unit, the host computer access the new second storage unit. Thus, merits of the new second storage unit, such as high performance, high functions, and high reliability of the second storage unit, can be enjoyed even when data actually stored in the existing first storage unit are accessed. In other words, the merits of the newly-installed storage unit can be applied to all the data including the data in the existing first storage unit. In addition, the existing storage unit and the new storage unit are used jointly, and storage capacity of the new storage unit can be smaller, and installation costs can be the smallest.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram showing a computer system as an embodiment of the present invention;
FIG. 2 is a diagram showing an example configuration of a logical device management information table in an embodiment of the present invention;
FIG. 3 is a diagram showing an example configuration of a RAID management information table in an embodiment of the present invention;
FIG. 4 is a diagram showing an example configuration of an external device management information table in an embodiment of the present invention;
FIG. 5 is a flowchart showing a procedure of installing a new storage unit in an embodiment of the present invention;
FIG. 6 is a flowchart showing a migration procedure at the time of migrating data from an existing first storage unit to a new second storage unit in an embodiment of the present invention;
FIG. 7 is a flowchart showing a procedure of processing an input-output request from a host to a new second storage unit in an embodiment of the present invention;
FIG. 8 is a flowchart showing a processing procedure at the time of adding a disk unit to a new second storage unit in an embodiment of the present invention; and
FIG. 9 is a diagram showing an example configuration of a logical device access statistical information table in an embodiment of the present invention.

BEST MODE OF PRACTICING THE INVENTION

Now, one embodiment of a computer system according to the present invention will be described.
As shown in FIG. 1, a computer system of the present invention comprises a host computer 11, a fibre channel switch 18; two storage units 12 a and 12 b (referred to as a storage unit 12, by a general term) and a management server 13. The host computer 11 is connected with the two storage units 12 a and 12 b through the fibre channel switch 18 and cables. Further, the host computer 11, the two storage units 12 a and 12 b and the fibre channel switch 18 are connected to the management server 13 through an IP network 142.
The host computer 11 comprises a CPU, a memory, and the like, and performs predetermined functions when the CPU reads and executes an operating system (hereinafter, referred to as OS) and application programs stored in the memory.
Among the two storage units 12 a and 12 b, a first storage unit 12 b is an existing storage unit, and a second storage unit 12 a is a newly installed storage unit. The first storage unit 12 b comprises a disk unit 121, a disk controller 122, a port 123 for connecting with the host computer 11, and a network interface 125 for connecting with the IP network 142. Here, the first storage unit 12 b may comprise a plurality of disk units and a plurality of ports. Further, the second storage unit 12 a comprises a plurality of disk units 121, a disk controller 122, a port 123 a for connecting with the host computer 11 and a plurality of ports 123 b for connecting with the other storage units (referred to as a port 123, by a general term), and a network interface 125 for connecting with the IP network 142.
In a storage unit 12 of the present embodiment, a disk unit or units 121 as hardware are defined collectively as one or a plurality of physical devices, and one logical device (i.e., one device from a logical viewpoint) is assigned to one physical device. Of course, it is possible to present an individual disk unit 121 as one physical device and one logical device, to the host computer 11.
As a port 123 of a storage unit 12 in the present embodiment, it is assumed to use the fibre channel interface whose upper protocol is SCSI (Small Computer System Interface). However, another network interface for storage connection, such as IP network interface whose upper protocol is SCSI, may be used.
A disk controller 122 of a storage unit 12 comprises a processor, a cache memory 124 and a control memory, and communicate with the management server 13 through the network interface 125 and controls the disk unit 121. The processor controls access from the host computer 11 and controls the disk unit 121, based on various kinds of information stored in the control memory. In particular, in the case where a plurality of disk units 121 (not a single disk unit 121) such as ones in a disk array are presented as one or plurality of logical devices to the host computer 11, the processor performs processing and management relating to the disk units 121.
The control memory stores programs executed by the processor and various kinds of management information. As one of the programs executed by the processor, there may be a disk controller program. This disk controller program includes an installation program for installing the second storage unit 12 a into a computer system. This installation program and the disk controller program including it are executed by the processor to function as a storage installation controller 129 and the disk controller, respectively. Further, as the various kinds of management information stored or to be stored in the control memory, there may be logical device management information 126 for management of the logical devices of the second storage unit 12 a; RAID (Redundant Array of Independent Disk) management information 127 for management of physical devices consisting of the plurality of disk units 121 of the second storage unit 12 a, and external device management information 128 for management of correspondence between the logical devices of the second storage unit 12 a and the logical devices of the first storage unit 12 b.
To enhance speed of processing an access from the host computer 11, the cache memory 124 stores data that are frequently read, or temporally stores write data from the host computer 11.
The host computer 11 is connected with the fibre channel switch 18 through an interface (I/F) 112, and also with the management server through a network interface 113. On the host computer 11, software (program) called a device link manager (hereinafter, referred to as DLM) 111 operates. The DLM 111 manages correspondence between the logical devices (recognized through the interface 112) of the storage unit 12 and device files as device management units of the OS. Usually, when a logical device is connected with a plurality of interfaces 112 and a plurality of ports 123, the host computer 11 recognizes that logical device as a plurality of devices having different addresses, and different device files are defined, respectively. A plurality of device files corresponding to one logical device are managed as a group by the DLM 11, and a virtual device file as a representative of the group is provided to upper levels, so that alternate paths and load distribution can be realized. Further, in the present embodiment, the DLM 111 also adds/deletes a new device file to/from a specific device file group and changes a main path within a device file group, according to an instruction from a storage manager 131 located in the management server 13.
The management server 13 performs operation, maintenance and management of the whole computer system. The management server 13 comprises a network interface 133, and connects with the host computer 11, the two storage units 12 a and 12 b, and the fibre channel switch 18, through the IP network 142. The management server 13 collects configuration information, resource utilization factors, performance monitoring information from various units 11, 12 and 18, presents them to a storage administrator, and sends operation/maintenance instructions to those units. The mentioned processing is performed by the storage manager 131 operating on the management server 13.
Similarly to the disk controller 122, also the storage manager 131 comprises a processor and a memory. The memory stores a storage manager program executed by the processor. This storage manager program includes an installation program for installing a new storage unit. This installation program and the storage manager program including it are executed by the processor to function as an installation controller 134 and the storage manager 131, respectively. When a new storage unit is installed, this installation program is installed onto the existing management server 13, except the case where a new management server incorporated with the installation program is employed.
The fibre channel switch 18 comprises a plurality of ports 181. Each port 181 is connected with the interface 112 of the host computer 11 or a port 123 of the storage unit 12 a or 12 b, so that each of those devices can communicate with another device. The fibre channel switch 18 comprises a network interface 182, and is connected with the IP network 142 also. Due to this arrangement, from the physical viewpoint, any host computer 11 can access all the storage units 12 a and 12 b connected to the fibre channel switch 18. Further, the fibre channel switch 18 has a function called zoning, i.e., a function of limiting communication from a specific port to another specific port. This function is used, for example, when access to a specific port 123 of a specific storage 12 is limited to a specific host 11. As a method of controlling combinations of a sending port and a receiving port, may be mentioned a method in which an identifier assigned to a port 181 of the fibre channel switch is used, and a method in which WWN (World Wide Name) held by the interface 112 of each host computer 11 and a port 123 of a storage unit 12, for example.
Next, there will be described the logical device management information 126, the RAID management information 127 and the external device management information 128 stored or to be stored in the control memory of the disk controller 122 of the second storage unit 12 a.
FIG. 2 is a diagram showing an example configuration of a logical device management information 126 for management of the logical devices within the second storage unit 12 a.
Each record of the logical device management information 126 includes a logical device number 21, a size 22, a corresponding physical/external device number 23, a device state 24, a port ID/target ID/LUN (Logical Unit number) 25, a connected host name 26, a migrating physical/external device number 27, a data migration progress pointer 28, and a data migration processing flag 29.
The size 22 stores capacity of the logical device, i.e., the logical device specified by the logical device number 21. The corresponding physical/external device number 23 stores a physical device number of the physical device corresponding to the logical device, in the second storage unit 12 a, or stores an external device number, i.e., a logical device of the first storage unit 12 b corresponding to the logical device. In the case where the corresponding physical/external device number 23 is not assigned with a device number, an invalid value is set in that entry. This device number becomes an entry number in the RAID management information 127 or the external device management information 128. The device state 24 is set with information indicating a state of the logical device. The device state can be “online”, “offline”, “non-installed”, “fault offline” or “data migration in progress”. The state “online” means that the logical device is operating normally, and can be accessed from an upper host. The state “offline” means that the logical device is defined and is operating normally, but, can not be accessed from an upper host. This state corresponds to a case where the device was used before by an upper host, but now is not used by the upper host since the device is not required. Here, the phrase “the logical device is defined” means that correspondence with a physical device or an external device is set, or, in detail, the physical/external device number 23 is set. The state “non-installed” means that the logical device is not defined and can not be accessed from an upper host. The state “fault offline” means that a fault occurs in the logical device and an upper host can not access that logical device. Further, the state “data migration in progress” means that data migration from or to an external device is in course of processing.
For the sake of simplicity, it is assumed in the present embodiment that, at the time of shipping of the product, available logical devices were assigned in advance to physical devices prepared on a disk unit 121. Accordingly, an initial value of the device state 24 is “offline” with respect to the available logical devices, and “non-installed” with respect to the other.
The port number of the entry 25 is set with information indicating which port the logical device is connected with, among the plurality of ports 123. As the port number, a number uniquely assigned to each port 123 within the storage unit 12 is used. Further, the target ID and LUN are identifiers for identifying the logical device. Here, when the host computer 11 accesses the device on SCSI, the target ID and LUN are used as a SCSI-ID and LUN, respectively. The connected host name 26 is information used only by the storage units 12 a and 12 b connected to the fibre channel switch 18, and shows a host name for identifying a host computer 11 that is permitted to access the logical device. As the host name, it is sufficient to use a name that can uniquely identify a host computer 11 or its interface 112, such as a WWN (World Wide Name) given to the interface 112 of a host computer 11. In addition, the control memory of the storage 12 a or 12 b holds management information on an attribute of a WWN and the like of each port 123.
When the device state 24 is “data migration in progress”, the migrating physical/external device number 27 holds a physical/external device number of a migration destination of the physical/external device to which the logical device is assigned. The data migration progress pointer 28 is information indicating the first address of a migration source area for which migration processing is unfinished, and is updated as the data migration progresses. The data migration processing flag 29 has an initial value “Off”. When the flag 29 is set to “On”, it indicates that the physical/external device to which the logical device is assigned is under data migration processing. Only in the case where the data migration processing flag is “On”, the migrating physical/external device number 27 and the data migration progress pointer 28 become effective.
FIG. 3 is a diagram showing an example configuration of the RAID management information 127 for management of the physical devices within the storage unit 12 a.
Each record of the RAID management information 127 includes a physical device number 31, a size 32, a corresponding logical device number 33, a device state 34, a RAID configuration 35, a stripe size 36, a disk number list 37, start offset in disk 38, and size in disk 39.
The size 32 stores capacity of the physical device, i.e., the physical device specified by the physical device number 31. The corresponding logical device number 33 stores a logical device number of the logical device corresponding to the physical device, within the second storage unit 12 a. In the case where the physical device is not assigned with a logical device, this entry is set with an invalid value. The device state 34 is set with information indicating a state of the physical device. The device state can be “online”, “offline”, “non-installed” or “fault offline”. The state “online” means that the physical device is operating normally, and is assigned to a logical device. The state “offline” means that the physical device is defined and is operating normally, but is not assigned to a logical device. Here, the phrase “the physical device is defined” means that correspondence with the disk unit 121 is set, or, in detail, the below-mentioned disk number list 37 and the start offset in disk 38 are set. The state “non-installed” means that the physical device is not defined on the disk unit 121. The state “fault offline” means that a fault occurs in the physical device, and the physical device can not be assigned to a logical device.
For the sake of simplicity, it is assume in the present embodiment that physical devices were prepared in advance on the disk unit 121 at the time of shipping of the product. Accordingly, an initial value of the device state 34 is “offline” with respect to the available physical devices, and “non-installed” with respect to the other.
The RAID configuration 35 holds information on a RAID configuration, such as a RAID level and the numbers of data disks and parity disks, of the disk unit 121 to which the physical device is assigned. Similarly, the stripe size 36 holds data partition unit (stripe) length in the RAID. The disk number list 37 holds a number or numbers of one or plurality of disk units 121 constituting the RAID to which the physical device is assigned. These numbers are unique values given to disk units 121 for identifying those disk units 121 within the storage unit 12. The start offset in disk 38 and the size in disk 39 are information indicating an area to which data of the physical device are assigned in each disk unit 121. In the present embodiment, for the sake of simplicity, the respective offsets and sizes in the disk units 121 constituting the RAID are unified.
Each entry of the above-described RAID management information 127 is set with a value, at the time of shipping the second storage unit 12 a.
FIG. 4 is a diagram showing an example configuration of the external device management information 128 of the second storage unit 12 a that manages the logical devices of the first storage unit 12 b as an external device.
Each record of the external device management information includes an external device number 41, a size 42, a corresponding logical device number 43, a device state 44, a storage identification information 45, a device number in storage 46, an initiator port number list 47, and a target port ID/target ID/LUN list 48.
The external device number 41 holds a value assigned to a logical device of the first storage unit 12 b, and this value is unique in the second storage unit 12 a. The size 42 stores capacity of the external device, i.e., the external device specified by the external device number 41. When the external device corresponds to a logical device in the second storage unit 12 a, the corresponding logical device number 43 stores a logical device number of that logical device. When the external device is not assigned to a logical device, this entry is set with an invalid value. The device state 44 is set with information indicating a state of the external device. The device state 44 is “online”, “offline”, “non-installed” or “fault offline”. The meaning of each state is same as the device state 34 in the RAID management information. In the initial state of the second storage unit 12 a, another storage unit is not connected, and the initial value of the device state 44 is “non-installed”.
The storage identification information 45 holds identification information of the first storage unit 12 b that carries. the external device. As the storage identification information, may be considered, for example, a combination of vendor identification information on a vendor of the storage unit 12 b and a manufacturer's serial number assigned uniquely by the vendor. The device number in storage 46 holds a logical device number (in the first storage unit 12 b) corresponding to the external device. The initiator port number list 47 holds a list of port numbers of ports 123 b (of the second storage unit 12 a) that can access the external device. When, with respect to the external device, LUN is defined for one or more ports 123 of the first storage unit 12 b, the target port ID/target ID/LUN list 48 holds port IDs of those ports and one or plurality of target IDs/LUNs assigned to the external device.
Next, operation of the storage administrator and the computer system following installation of the second storage unit 12 a in the present embodiment will be described according to the flowchart shown in FIG. 5.
First, the storage administrator connects the second storage unit 12 a to the fibre channel switch 18 (Step 501). In the present embodiment, the port 123 a is connected to a port 181 of the fibre channel switch 18, for access from the host computer 11. And, the port 123 b is connected to a port 181 of the fibre channel switch 18, for access to other storage units including the first storage unit 12 b. When the second storage unit 12 a is activated, the fibre channel switch 18 detects the established links with the ports 123 a and 123 b of the second storage units 12 a. Thereafter, on occurrence of a login from each port 123 a or 123 b to the switch 18, a login to the interface or the port of the host computer 11 or the second storage unit 12 a is executed according to the fibre channel standard. At that time, the second storage unit 12 a holds information such as the WWN or ID of the host computer 11 or the like to which the port 123 a or 123 b has logged in. Receiving a state change notification from the switch 18, the installation controller 134 of the storage manager 131 acquires network topology information from the switch 18 again, to detect new registration of the second storage unit 12 a.
Processing on and after the step 502 is performed mainly by the installation controller 134 of the storage manager 131 that receives an instruction from the storage administrator to start installation of the second storage unit 12 a, and by the installation controller 129 of the second storage unit 12 a. In the step 502, the installation controller 134 of the storage manager 131 changes zoning setting of the switch 18, and changes device access right setting of the first storage unit 12 b such that the second storage unit 12 a can access the devices of the first storage unit 12 b.
In the step 503, the storage manager 131 assigns the logical devices of the first storage unit 12 b to the logical device of the second storage unit 12 a. In detail, first, the storage manager 131 sends the second storage unit 12 a the port ID list of the first storage unit 12 b as the object of migration to the second storage unit 12 a. From the port 123 b, the installation controller 129 of the second storage unit 12 a sends a SCSI “Inquiry” command that designates a specific LUN for a port 123 (of the first storage unit 12 b) existing in the received list, with respect to all such LUNs. On the other hand, the processor of the first storage unit 12 b responds normally to “Inquiry” commands relating to LUNs that are actually set to the port IDs of the first storage unit 12 b. Based on this response, the installation controller 129 of the second storage unit 12 a specifies the logical devices (of the first storage unit 12 b) that can be accessed and migrated to the second storage unit 12 a. And, the installation controller 129 generates an external device list (from the viewpoint of the second storage unit 12 a) of those logical devices. To judge whether migration is possible or not, the installation controller 129 utilizes information such as names, types and capacities of devices connected to the second storage unit 12 a. The information such as the names, types and capacities of the devices is acquired from returned information of the response to the above-mentioned “Inquiry” command and returned information of a response to “Read Capacity” command that is sent after the “Inquiry” command. With respect to logical devices (of the first storage unit 12 b) whose migration has been judged to be possible, the installation controller 129 registers those logical devices as external devices of the second storage unit 12 a into the external device management information 128. In detail, the installation controller 129 finds an external device whose device state 44 is “non-installed”, and sets information 42˜48 into the entries concerned of that external device. Now, the device state 44 is changed to “offline”.
The installation controller 129 of the second storage unit 12 a notifies the storage manager 131 of the above-mentioned external device list with respect to the designated port. And, the installation controller 134 of the storage manager 131 instructs the second storage unit 12 a to assign the logical devices of the first storage unit 12 b. Receiving this instruction, the installation controller 129 of the second storage unit 12 a assigns an external device a, i.e., a logical device of the first storage unit 12 b, to a non-installed logical device a of the second storage unit 12 a. In detail, the installation controller 129 of the second storage unit 12 a sets the device number 41 of the external device a to which the logical device of the first storage unit 12 b corresponds, into the corresponding physical/external device number 23 of the logical device management information 126 relating to the logical device a. Then, the installation controller 129 of the second storage unit 12 a changes the device state 24 of the logical device management information 126 from “non-installed” to “offline”. In addition, the corresponding logical device number 43 of the external device management information 128 is set to the device number 21 of the logical device a, and the device state 44 is changed to “online”.
Successively, in the step 504, the installation controller 134 of the storage manager 131 instructs the second storage unit 12 a to define a LUN to the port 123 a such that the host computer 11 can access the logical device a assigned to the second storage unit 12 a. Receiving this instruction, the installation controller 129 of the second storage unit 12 a defines a LUN relating to the above-assigned logical device a, i.e., defines a device path to the port 123 a of the second storage unit 12 a. Then, the port number/target ID/LUN 25 and the host name 26 of the logical device management information 126 are set.
When the logical device of the first storage unit 12 b is assigned as the logical device of the second storage unit 12 a, and also the LUN is defined, then, the installation controller 134 of the storage manager 131 instructs the DLM 111 of the host computer 11 to recognize the devices again. Receiving this instruction, the DLM 111 of the host computer generates a device file relating to the newly-assigned logical device. For example, in the case of the UNIX (a registered trademark) operating system of Hewlett-Packard Ltd., an “IOSCAN” command is used to recognize a new logical device and to generate a device file. When the logical device of the storage unit 12 corresponding to the newly-generated device file is same as one corresponding to a previously-generated device file, then, the DLM 111 detect it and manages these device file as a same group. To judge the sameness, it is considered to use the above-mentioned “Inquiry” command or the like to acquire the device number in the storage 12, for example. However, in the case where a logical device b in the first storage unit 12 b corresponds to a logical device a in the second storage unit 12 a, the DLM 111 sees these logical devices a and b as logical devices of the different storage units 12 a and 12 b, they are not managed in a same group.
Next, the installation controller 134 of the storage manager 131 instructs the DLM 111 of the host computer 11 to change the access destination. Receiving this instruction, the DLM 111 changes access to the device in the first storage 12 b to access to the device in the second storage unit 12 a (Step 506). In detail, first, the installation controller 134 of the storage manager 131 sends device correspondence information of the first storage unit 12 b and the second storage unit 12 a to the DLM 111. The device correspondence information is information of the assignment of the logical devices of the second storage unit 12 b. The DLM 111 of the host computer 11 assigns a virtual device file that is assigned to a device file group relating to a logical device b in the first storage unit 12 b to a device file group relating to a logical device a in the second storage unit 12 a. As a result, software operating on the host computer 11 can access the logical device a in the second storage unit 12 a according to a same procedure of accessing the logical device b in the first storage unit 12 b.
Next, in the step 507, the installation controller 134 of the storage manager 131 makes the switch 18 change the zoning setting and makes the first storage unit 12 b change setting of the device access right, to inhibit the host computer 11 from directly accessing the devices of the first storage unit 12 b.
Next, referring to the flowchart shown in FIG. 6, there will be described processing of migrating data stored in the devices in the first storage unit 12 b to an empty device in the second storage unit 12 a, after installation of the second storage unit 12 a into the computer system.
First, the installation controller 134 of the storage manager 131 instructs the second storage unit 12 a to migrate data. In the step 601, the installation controller 129 of the second storage unit 12 a checks the device state 34 of the RAID management information 127, to search for a physical device a in the “offline” state, i.e., in an empty state. When a physical device in the “offline” state is found, then, the size 32 is referred to in order to obtain the capacity of the empty device. Next, in the step 602, the installation controller 129 searches for such an external device (hereinafter, referred to as the migration object device) that the device state 44 of the external device management information 128 is “online” and the size 42 of the external device management information 128 can be accommodated by the capacity of the physical device a.
When the empty physical device a as the migration destination and the migration object device are determined, then, in the step 603, the installation controller 129 assigns an empty physical device to the logical device a of the second storage unit 12 a (Step 603). In detail, the installation controller 129 registers the number of the logical device a into the corresponding logical device number 33 of the RAID management information 127 corresponding to the physical device a, and changes the device state 34 from “offline” to “online”. Further, after initializing the data migration progress pointer 28 of the logical device management information 126 corresponding to the logical device a, the device state 24 is set to “data migration in progress”, the data migration processing flag 29 is set to “On”, and the migrating physical/external device number 27 is set to the device number of the physical device a.
When the device assignment is finished, then, in the step 604, the installation controller 129 of the second storage unit 12 a performs processing of data migration from the migration object device to the physical device a. In detail, from the top of the migration object device, data are read to the cache memory 124, and then, the data are written onto the physical device a. This operation is repeated to the end of the migration object device. In the course of this operation, each time when writing onto the physical device a is finished, the first address of the next migration object area is set into the data migration progress pointer 28.
When migration of all the data is finished, then, in the step 605, the installation controller 129 sets the corresponding physical/external device number 23 of the logical device management information 126 with the physical device number of the physical device a, and the device state 24 is changed from “data migration in progress” to “online”, the data migration flag 29 is set to “Off”, and the migrating physical/external device number 27 is set to the invalid value. Further, the corresponding logical device number 43 of the external device management information 128 corresponding to the migration object device is set to the invalid value, and the device state 44 is set to “offline”.
Next, referring to the flowchart shown in FIG. 7, there will be described operation of the second storage unit 12 a in response to an input-output request from the host computer 11.
When the installation controller 129 of the second storage unit 12 a receives an input-output request from the host computer 11 (Step 701), the installation controller 129 judges whether the request is read or write (Step 702). In the case where the request is read, it is checked whether processing object data are held in the cache memory 124 (hit) (Step 703). When the processing object data are not held in the cache memory 124, data staging to the cache memory 124 is performed. At that time, it is judged whether the data migration is in progress, based on the device state 24 of the logical device in the logical device management information 126. When the data migration is in progress, then, it is judged whether a processing object address of the logical device as the processing object is in a migrated data area, based on the data migration progress pointer 28 relating to the logical device in the logical device management information 126 (Step 704). In the case where the data migration is in progress and data of the processing object area has been migrated already, then, read processing is performed for reading from the migration destination device indicated by the migrating physical/external device number 27 (Step 706). In the other case, read processing is performed for reading from the migration object device indicated by the corresponding physical/external device number 23 (Step 705).
In the read processing in the step 705, the installation controller 129 converts the read request from the host computer 11 into a read request to the migration object device indicated by the corresponding physical/external device number 23, and sends the converted request to the first storage unit 12 b. Receiving this read request, the first storage unit 12 b performs read processing toward the disk unit 121 corresponding to the above-mentioned migration object device, and sends read contents to the second storage unit 12 a. Further, in the read processing in the step 706, the read processing is performed toward the migration object device indicated by the migrating physical/external device number 27.
When, after execution of the read processing (Step 705 or 706), the data staging to the cache memory 124 is finished, then, the object data held in the cache memory 124 is transferred to the host computer 11 (Step 707). And, the disk controller 122 of the second storage unit 12 a sends a completion report to the host computer 11 (Step 708).
When it is judged in the step 703 that cache hit occurs, then, the object data held in the cache memory 124 are immediately transferred to the host computer 11 (Step 707).
When the data transfer to the host computer 11 is finished, the disk controller 122 of the second storage unit 12 a sends a processing completion report to the host computer 11 (Step 708).
When it is judged in the step 702 that the input-output request from the host computer 11 is write, then, the disk controller 122 of the second storage unit 12 a assigns a write data storage area to the cache memory 124, transfers write data from the host computer 11 to the cache memory 124, and sends a completion report to the host computer 11 (Steps 709-711). Thereafter, destaging of the write data is performed.
In the course of the destaging, it is judged whether the logical device is under data migration, based on the device state 24 of the logical device management information 126 (Step 712). When the logical device is under data migration, then, write processing of the above-mentioned data is performed toward both the migration source (migration object) device and the migration destination device (Step 713). On the other hand, when the logical device is not under data migration, write processing of the above-mentioned data is performed toward the device indicated by the corresponding physical/external device number 23 (Step 714).
Next, referring to the flowchart shown in FIG. 8, there will be described data migration processing in the case where a disk unit 121 is added to the second storage unit 12 a.
First, when the storage administrator adds a disk unit 121 to the second storage unit 12 a, and the installation controller 129 of the second storage unit 12 a detects this addition (Step 801), then, the installation controller 129 defines a new empty device, i.e., a physical device of an “offline” state (Step 802). At that time, the entries 32-39 of the RAID management information 127 are updated.
Thereafter, data migration of an external device whose data are not migrated yet is performed toward the newly-assigned empty device (Steps 803-806). These processes (Steps 803-806) are similar to the steps 602-605 of FIG. 6, and not described here again.
Hereinabove, an embodiment of the present invention has been described. However, the present invention is not limited to the above-described embodiment, and can be modified variously within the scope of the present invention.
For example, in the processing of installing the second storage unit 12 a to the computer system, which has been described referring to FIG. 5, the port ID list of the first storage unit 12 b as the migration object is sent from the storage manager 131 to the second storage unit 12 a, in the step 503. However, instead of the port ID list, information that can specify the first storage unit 12 b (for example, identification information list for identifying the unit name obtainable by an “Inquiry” command) may be sent. Identification information of the mentioned list is information required by the storage manager 131 to manage the first storage unit 12 b, and although basically held inside the storage manager 131, may be obtained by sending an “Inquiry” command to the first storage unit 12 b at the time of sending the list. In that case, the second storage unit 12 a sends an “Inquiry” command to all the storage node ports that can be reached from the port 123 b, and compares the above-mentioned identification information list with unit identification information among information obtained from the first storage unit 12 b, so that only coincident ports become migration objects. Further, it is possible that the second storage unit 12 a does not receive an instruction from the storage manager 131 and all the storage node ports reachable from the port 123 b become migration objects.
Further, in the step 503 during installation processing of the second storage unit 12 a, the storage manager 131 is notified of the list of the external devices detected by the second storage unit 12 a, and only the external devices designated by the storage manager become the migration objects. However, it is possible that the second storage unit 12 a does not notify the storage manager 131 of the detected external device list, and all the devices shown in the external device list become migration objects.
Further, in the step 503, the second storage unit 12 a selects and assigns the non-installed logical device to the external device designated by the storage manager 131. However, the storage manager 131 may determine a non-installed logical device as an object of assignment and indicate the determined logical device to the second storage unit 12 a. In that case, the storage manager 131 must obtain information such as the logical device number 21 and the device state 24 out of the logical device management information 126 shown in FIG. 2, to determine migration objects based on the obtained information.
Further, as described referring to the flowchart of FIG. 6, in the step 601 during the migration processing from an external device, i.e., a logical device of the first storage unit 12 b, which is assigned to a logical device of the second storage unit 12 a, to an empty physical device of the second storage unit 12 a, the second storage unit 12 a performs data migration from the external device to all the empty physical devices as the migration destination. However, it is possible to limit migration destination physical devices, based on control information that can be used to judge whether a physical device can be a migration object. In detail, a data migration target availability flag is provided to each record of the RAID management information shown in FIG. 3. This flag is set with a flag value indicating whether each physical device can become a data migration destination at the time of initialization or addition of a physical device. Based on this information, the second storage unit 12 a specifies a physical device that can be a migration destination. Here, the mentioned flag value is set by the storage administrator using a configuration management terminal (not shown in FIG. 1) of the second storage unit 12 a, or using an input-output unit such as a keyboard and/or a mouse provided to the storage manager 131. For example, it is possible to employ an arrangement in which a flag value is automatically set to “unavailable as migration target” as a basic set value given at the time of installation of a physical device, and the storage administrator changes the flag value relating to a specific physical device to “available as migration target”. Or, it is possible to employ an arrangement in which, as the basic set value, the value “available as migration target” is set automatically, and the storage administrator changes the flag value relating to a specific physical device to “unavailable as migration target”.
Further, it is possible that, with respect to a data migration instruction of the storage manager 131, the storage manager 131 holds physical device information such as the physical device number 31, the size 32 and the device state 34 out of the RAID management information 127 shown in FIG. 3, and specifies an empty physical device as the data migration destination, to the second storage unit 12 a. In that case, in the data migration processing (shown in FIG. 6) of the second storage unit 12 a, it is necessary to add a step in which it is checked whether the specified physical device is empty and the data migration request is rejected when the specified physical device is not empty.
Further, in the processing of the step 602 shown in FIG. 6, when the second storage unit 12 a determines the migration object external device, the external device is determined by checking only whether it can be accommodated by the size of the empty physical device selected in the step 601. However, the migration object may be determined based on other information of the external device. For example, it is possible that a data migration object possibility flag is provided to each record of the external device management information 128 shown in FIG. 4, and it is judged whether the external device can be an object of migration. In that case, when the external device management information 128 on an external device is registered in the step 503, the above-mentioned flag is initialized to have a value indicating possibility or impossibility of migration, and thereafter, the storage administrator changes the flag value. When the storage administrator changes the flag value, a configuration management terminal (not shown in FIG. 1) of the second storage unit 12 a, or an input-output unit such as a keyboard and/or a mouse provided to the storage manager 131 may be used. Further, instead of the above-mentioned data migration object possibility flag, data migration object priority information may be provided. In that case, the second storage unit 12 a determines the migration object external device, referring to the migration object priority information set by the storage administrator.
Further, as a standard for determining a migration object external device, host access statistical information to the external device may be used, for example. In detail, the second storage unit 12 a acquires access statistical information for each logical device. FIG. 9 shows an example of the statistical information. In each record of the access statistical information, an access frequency 91 indicates the number of accesses per time unit to the logical device, and a read frequency 92 indicates the number of reads per time unit from the logical device. A write frequency can be calculated from the access frequency 91 and the read frequency 92. A read cache hit rate 93 and a write cache hit rate 94 are hit rates in the cache memory 124 of the second storage unit 12 a at the time of read access and at the time of write access, respectively. By combining these information items, it is possible to calculate an access frequency of each logical device to the corresponding external device (device of the first storage unit 12 b). Here, as a data migration object, it is possible to select such an external device that has a higher access frequency and can be accommodated by the size of an empty device, based on thus-obtained access frequency for each external device.
Further, in the data migration processing shown in FIG. 6, the storage manager instructs the second storage unit 12 a to perform data migration. However, the second storage unit 12 a may automatically perform the data migration processing, as an extension of the processing of associating an external device, i.e., a logical device of the first storage unit 12 b, with a logical device of the second storage unit 12 a. Namely, out of the various functions of the installation controller 134 of the storage manager 131, the functions relating to the data migration processing shown in FIG. 6 may be mounted on the second storage unit 12 a.

Claims

1. A storage unit installation method for newly installing a second storage unit having one or more storage devices into a computer system comprising a first storage unit having one or more storage devices and a host computer accessing said first storage unit, wherein:

said second storage unit is connected with said host computer and said first storage unit in such a way that input and output of information are possible;

access right setting of said first storage unit is changed such that the second storage unit can access the first storage unit;

a logical device (hereinafter, referred to as a first logical device) relating to said one or more storage devices of the first storage unit is assigned to a logical device (hereinafter, referred to as a second logical device) of the second storage unit;

path definition with respect to said second logical device and device recognition in said host computer are performed such that the host computer can access the second logical device of the second storage unit; and

input-output setting of said host computer is changed such that said second storage unit is requested to processing of input-output from said host computer to said one or more storage devices of said first storage unit.