JP2000148652A - Disk array control method and disk array controller - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce cost even at the time of adopting a high speed interface. SOLUTION: A disk array controller 1, disk device 2 and host 3 are all connected to one interface 31, and communication between the disk array controller 1, and the host 3 and communication between the disk array controller 1 and the disk device 2 is operated through one host interface 31. Thus, it is possible to reduce cost, even when a high-speed interface such as a fiber channel is adopted. Especially, an I/F controller 12 of the disk array controller 1 is shared for both the host and the disk device so that cost can be reduced further.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a disk array control method and a disk array control device, and more particularly, to a disk array control method and a disk array control device capable of realizing low cost and high speed.

[0002]

2. Description of the Related Art (1) A RAID disk array is a technique for realizing high speed by operating a plurality of disk devices in parallel. However, when n (> 1) disk devices are arranged, the failure probability is n.
It gets worse twice. Therefore, as a technology for achieving both high speed and high reliability, “RAID (Redundant Arrays of In
expensive Disks) ". In addition, RAID
For more information about "A Case for Redundant Arrays of
Inexpensive Disks (RAID) "; In Proc. ACM SIGMOD, J
l2_systemmessage [1988] = _strdup (1988) (published by the University of California, Berkeley).

[0003] RAID achieves high speed by operating a plurality of disk devices in parallel. Also, redundant data called parity is stored in a parity disk device, and one of the data disk devices storing data is stored in the disk device.
When a table fails, high reliability is realized by restoring data of the failed data disk device from data of another data disk device and parity of the parity disk device. RAID has levels 1 to 5 depending on the method of storing the parity.

FIG. 13 shows an example of a data layout diagram of a level 4 RAID. In this example, there are five disk drives, four of which are data disk drives 200-2.
03, if one is a parity disk device 204,
Data is divided into data blocks D0, D1, D2,
D3 is divided and stored in the order of the data disk device 200, the data disk device 201, the data disk device 202, and the data disk device 203. These data blocks are called stripes, and this distributed control is called striping. further,
The exclusive OR of the stripes D0 to D3 is calculated, a parity P0 is generated, and the parity P0 is stored in the parity disk device 204. Stripes and parities in the same column for generating one parity are called a parity group. In addition to level 4, levels 3 and 5 generate parity in the same manner as above. Note that a group of disk devices constituting a RAID is referred to as a RAID group.

For example, data (D0, D1, D2, D
3) When data is to be read, the data disk device 200
, The data D1, D2, D3 and the parity P0 are read, the exclusive OR of them is calculated, and the data D0 is restored.

(2) Disk Array Controller In order to realize the RAID type disk array as described above, a read / write request from a host (host computer) is converted into a read / write request to each disk device, and a write is performed. Sometimes data is distributed to each disk device,
At the time of reading, it is necessary to perform data distribution / set control for collecting data from each disk device. Further, it is necessary to perform parity generation control for calculating parity. To perform these controls, usually, a disk array controller called a disk array controller is provided between the host and the plurality of disk devices.

FIG. 14 shows a first example of a conventional computer system. The computer system 500 includes a host 3 and a disk array 4. A host interface 31 connects the host 3 and the disk array controller 4.

The disk array 4 includes the disk array controller 1 and disk devices 200 to 204. 210 to 214 are disk array controllers 1
And a disk interface for connecting the disk devices 200 to 204.

The disk array controller 1 is a central control means 1 for controlling the entire disk array controller.
0, data cache means 11 for temporarily storing data for data distribution / concentration and using it as a cache, a host I / F controller 120 for controlling the host interface 31, and disk interfaces 210 to 214 Are provided.

The host interface 31 and the disk interfaces 210 to 214 have SCSI (Small)
Computer System Interface). Therefore, such a disk array is referred to as a SCSI disk array.

(3) Fiber Channel In recent years, Fibre has a high performance with respect to SCSI and a long connection distance.
bre Channel (hereinafter abbreviated as FC) has appeared. Fiber Channel uses a point-to-point topology in which a host and a disk array are connected one-to-one, a loop topology in which a plurality of hosts and a disk array are connected in a loop configuration, and a switch device called a fabric. -It can take three forms of switch topology in which a large network can be built with any combination of points and loops. In particular, the loop topology is FC-AL (FibreChannel-Arb).
It is called SAN (Stored Loop), which is a network that interconnects multiple hosts and multiple storages.
age Area Network). Also, FC-
AL has also been used for disk device interfaces 210-214. FC-AL is SCS
In addition to the advantages of performance and connection distance for I, disk drives can be hot-swapped, the number of connected disk devices is as many as 126 per loop, and the serial cable is easy to route. It has a preferred function to apply to the device interface.

(4) FC type disk array FIG. 15 shows a second example of a conventional computer system. The computer system 600 uses the FC-AL for the host interface 31 and the disk interface 1
3 also uses FC-AL. The host host interface 31 includes a plurality of hosts 3, 3a, 3b
Are connected, and a plurality of disk arrays 4, 4
a is also connected. The disk array controller 1 of the disk array 4 has one disk interface 13
Is a loop configuration in which a plurality of disk devices 200 to 204 are connected. There is one disk I / F controller 130 for controlling the disk interface 13. Such a disk array will be referred to as an FC disk array.

An example of using Fiber Channel as a host interface is described in "Nikkei Electronics 1994.7.4 (no.612)".
No. Special Issue “Exploring post-SCSI design philosophy. Comparing three new interfaces” p.128 ”.
An example of using re Channel for the disk interface is shown on page 131 of the same document.

(5) Multi-port I / F In the case of the SCSI disk array 4 shown in FIG.
A plurality of disk devices 200 to 2 forming an ID group
04 different disk interfaces 210
By connecting to 214, operation can be continued even if one disk interface fails. Further, when a plurality of host interfaces 31 are prepared and connected to the disk array 4 from the same host 3 via the plurality of host interfaces 31, the host interface 31 can also have fault tolerance. Such a configuration having a plurality of host interfaces and a plurality of disk interfaces is referred to as a multi-port I / F. On the other hand, a configuration having only one host interface and one disk interface is called a single port I / F. Even in the FC disk array, it is necessary to provide a multi-port I / F in order to provide fault tolerance, and two I / Fs are provided for each.

[0015]

Problems to be Solved by the Invention (1) Problems of Cost Increase The FC type disk array (FIG. 15) can realize performance and functions exceeding the SCSI type disk array (FIG. 14).
However, the I / F control means for Fiber Channel is S
Since the I / F control means for CSI is very expensive, using Fiber Channel for both the host interface and the disk interface has a problem that the cost of the disk array controller increases. This issue is not limited to Fiber Channel;
Higher speed interfaces tend to be more expensive, so other high speed interfaces have similar problems. With the multi-port I / F, higher cost is further promoted.

(2) Problems of Response Time Degradation and Technical Difficulties Regardless of the conventional FC type disk array or SCSI type disk array, when data is read from the disk device to the host, the disk device uses the disk array. After buffering some or all of the data inside the control device, the data is transferred to the host. Therefore, there is a problem that the response time is reduced. Fiber Ch for both host interface and disk interface
When annel is used, the transfer speed of both is 100M
Assuming that the B / S is used, in order to realize data transfer that maximizes the bandwidth, the transfer speed inside the disk array controller is required to be at least 200 MB / S, and a high-speed data bus is required. Also, if the disk device is RA
In the case of ID, it is necessary to generate parity in parallel with data transfer. Therefore, the cache memory inside the disk array controller has a bandwidth of 200 required for data transfer.
In addition to MB / S, a bandwidth of 100 MB / S is required. In the case of a dual controller configuration, one disk array controller receives data from the host and performs a dual write to transfer the data to the other disk array controller. Further, a bandwidth of 100 MB / S for writing all data is required. From the above,
100MB / S host interface / disk interface pair, 200MB / S on data bus
A transfer band of S and a transfer band of 400 MB / S are required for the cache memory. Furthermore, a multi-port I / F is provided for n pairs of host interfaces and disk interfaces.
In this case, the data bus and the cache memory each require n times the transfer bandwidth in order to exhibit the performance of the multiport. As described above, the transfer speed inside the disk array controller requires a very high transfer band due to the increase in the speed of the interface and the increase in the number of ports. For this reason, it is necessary to improve the operating frequency of the internal bus and the cache memory and to increase the number of bits. In addition, there is a problem that even if the transfer speed is feasible, the cost becomes very high.

Accordingly, a first object of the present invention is to provide a disk array control method and a disk array control device which can reduce the cost even if a high-speed interface is used. The second object of the present invention is to
Responsibility can be improved, high-speed interface performance can be maximized, and the transfer speed inside the disk array controller can be kept low, technically easy to develop and cost reduction can be achieved. And to provide a disk array control method and a disk array control device.

[0018]

In a first aspect, the present invention provides a host and a disk array for controlling a plurality of disk devices to logically operate as one or more disk array devices as viewed from the host. A controller and the plurality of disk devices are connected to one host interface, and communication between the disk array controller and the host and communication between the disk array controller and the plurality of disk devices are performed by one host interface. And a disk array control method characterized in that the method is performed via In the disk array control method according to the first aspect, since the communication between the disk array control device and the disk device is also performed by using the host interface for performing the communication between the disk array control device and the host, the interface is one. And cost reduction can be achieved even with a high-speed interface.
In particular, if the I / F control means of the disk array control device is shared for the host and the disk device, the cost can be further reduced.

According to a second aspect, the present invention is directed to a host interface connected to a host and a plurality of disk devices, wherein the plurality of disk devices are logically connected to one or more disks as viewed from the host. A disk array controller for controlling operation as an array device, an I / F controller for controlling a host interface, a host command controller for performing processing such as receiving a command from a host, and interpreting a host command Transfer mode control means for determining a transfer path and a transfer mode between the host, the disk array control device, and the plurality of disk devices according to the result, and the determined transfer path, transfer mode, and disk array configuration From the address specified in the host command to the address of the disk device based on the There is provided a disk array control device comprising: an address conversion control unit that generates a disk command to a corresponding disk device; and a disk command control unit that performs processing such as issuing a disk command to the disk device. . In the disk array control device according to the second aspect, the disk array control method according to the first aspect can be suitably implemented.

In a third aspect, the present invention provides the disk array controller according to the second aspect, wherein the transfer mode control means reads "data from the disk device to the disk array controller when the host command is read. Transfer, and then a normal transfer in which data is transferred from the disk array controller to the host "can be selected as the transfer mode. When the host command is a write," the data is transferred from the host to the disk array controller and then the disk array A disk array control device characterized in that "normal transfer for transferring data from a control device to a disk device" can be selected as a transfer mode. In the disk control device according to the third aspect, the disk array control method according to the first aspect can be implemented using a conventional host and disk device.

In a fourth aspect, the present invention provides the disk array controller according to the second or third aspect, wherein the transfer mode control means reads "from the disk device to the disk array controller when the host command is read." Direct transfer that transfers data directly to the host without going through
At least when the host command is write, and when the host command is a write, `` direct transfer for directly transferring data from the host to the disk device without passing through the disk array controller '' can be selected as the transfer type. There is provided a disk array control device characterized in that one of them is possible. In the disk controller of the fourth aspect, since data is directly transferred between the host and the disk device without passing through the disk array controller, the responsiveness can be improved and the performance of the high-speed interface can be maximized. And the transfer speed inside the disk array controller can be kept low. Therefore, it can be developed technically easily, and the cost can be reduced. Also,
The processing load on the disk array controller can be reduced.

According to a fifth aspect, the present invention provides the disk array control device according to the second to fourth aspects, wherein the transfer mode control means reads from the disk device when a host command is read and a cache miss occurs. Multi-target direct transfer for transferring data to both the disk array controller and the host "can be selected as the transfer mode, and when the host command is write,
A disk array control device characterized in that at least one of a multi-target direct transfer for transferring data from the host to both the disk array control device and the disk device can be selected as a transfer mode. I do. In the disk controller of the fifth aspect, since data is directly transferred between the host and the disk device without passing through the disk array controller, responsiveness can be improved, and the performance of the high-speed interface is maximized. And the transfer speed inside the disk array controller can be kept low. Therefore, it can be developed technically easily, and the cost can be reduced. Further, the processing load on the disk array control device can be reduced. In addition, since data is also transferred to the disk array control device, an improvement in responsiveness by the cache can be expected. Further, if the multi-target direct transfer is performed when the host command is a write, the parity can be quickly generated by the disk array controller.
This is useful for ID.

According to a sixth aspect of the present invention, there is provided a host connected to a host interface to which the disk array control device and the disk device are connected, wherein host interface control means for controlling the host interface; And host transfer mode control means for controlling the host interface control means so as to receive the information on the transfer mode sent to the host device and perform data transfer with the disk device or the disk control device according to the information. Provide a host.
The use of the host according to the sixth aspect enables the disk array control method to be suitably implemented.

According to a seventh aspect, the present invention provides a disk device connected to a host interface to which the disk array control device and the host are connected, wherein the disk interface control means for controlling the host interface; Disk transfer mode control means for receiving the transfer mode information sent to the interface and controlling the disk interface control means so as to perform data transfer with the host or the disk array control device according to the information. A disk device is provided. The use of the disk device according to the seventh aspect enables the disk array control method to be suitably implemented.

According to an eighth aspect of the present invention, the disk array control device, the host, and the disk device are connected to a host interface, and all three perform data transfer in the same transfer mode. A computer system is provided. In the computer system according to the eighth aspect, the disk array control method can be suitably performed.

[0026]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings. Note that the present invention is not limited by this.

[First Embodiment] (Example of Normal Transfer) In the first embodiment, a transfer mode called "normal transfer" which is one of the transfer modes provided in the disk array of the present invention will be described. “Normal transfer” is a transfer mode in which data is transferred only between the host and the disk array controller, and between the disk array controller and the disk device. This is the same as the transfer form of the conventional disk array, but differs from the conventional one in that the host interface and the disk interface are integrated into one interface as described later.

(1) Configuration of Disk Array FIG. 1 shows a configuration example of a computer system according to the first embodiment. The computer system 100 includes a host 3, a host interface 31, and a disk array 4. The host interface 31 is FC-AL. The disk array 4 includes a disk array controller 1 and disk devices 200 to 204 (these are collectively referred to as a disk device 2). Although shown in a simplified manner in FIG.
4 is connected to the host interface 31. (2) Configuration of Disk Array Controller The disk array controller 1
, A data cache unit 11 and an I / F control unit 12
, A parity operation means 14 and an internal bus 15. The I / F control unit 12 sets the I / F control unit 12 to the target mode when used for communication with the host 3 and the I / F control unit 12 when used for communication with the disk device 2.
There is provided an initiator / target switching unit 121 for performing control to switch the F control means 12 to the initiator mode.

The central control means 10 includes an MPU (Micro P
rocessing Unit). Various control units are realized by a control program that operates on the MPU. FIG. 2 shows the configuration of the central control means 10. The central control unit 10 operates the I / F control unit 12 and performs communication with the host 3 such as receiving a command from the host 3. The host command control unit 101 analyzes the received host command and performs a cache hit miss. A transfer mode control unit 102 that performs a determination and a sequentiality determination of an access to determine a data transfer mode such as a transfer path between the host 3, the disk array controller 4, and the disk device 2 for each command; An address conversion control unit 103 that converts a logical address to the disk array 4 into a physical address to the disk device 2, generates a disk command, operates the I / F control unit 12, and issues a command to the disk device 2. And a disk command control unit 104 for performing communication with the disk device 2.

In the above description, the address of the disk device 2 is referred to as a physical address.
A disk device having a nel as an I / F operates using a logical address (LBA: logical block address). However, here, the disk array 4
Are referred to as one disk device, an address used for accessing the disk device is called a logical address, and an address of the disk device used for accessing the disk device 2 is called a physical address, so that the two are distinguished.

The transfer mode control unit 102 is also used in the first embodiment, but can be omitted when operating only with "normal transfer".

(3) Configuration of Host and Disk Unit Returning to FIG. 1, the host 3 includes a host I / F control unit 32 for connecting the disk array controller 1. Note that the host 3 includes the host transfer mode control unit 33, but the host transfer mode control unit 33 is not used in the first embodiment (used in the second and subsequent embodiments).
Therefore, it will not be described. Therefore, in the case of operating only with the "normal transfer" in the first embodiment, the host transfer mode control means 33
Can be omitted.

Each of the disk devices 200 to 204 has a disk I / F control unit 21. Each of the disk devices 200 to 204 includes the disk transfer mode control unit 22.
2 is not used in the first embodiment (used in the third and subsequent embodiments), and will not be described. Therefore, when operating only in the first embodiment "normal transfer", the disk transfer mode control means 22 can be omitted.

(4) Access Types In general, types of accesses are roughly classified into random access and sequential access. The random access is an access for reading and writing an arbitrary address in the logical address space of the disk array 4. Occurs when database records are referenced. In general, random access is often performed with a small transfer length of about 4 KB. In random access, the transfer time is short because the data transfer length is short. Therefore, during the entire processing time, the seek and rotation waiting time of the disk device are dominant. For sequential access, the disk array 4
This is an access to read and write successive logical addresses continuously. Occurs in batch processing and image access.
In general, sequential access is often performed with a large transfer length such as 64 KB. In sequential access, seek of the disk device hardly occurs due to continuous access, and during sequential read, data is pre-read inside the disk device, so there is almost no rotation waiting, but the transfer time is long because the data transfer length is long . Therefore, the data transfer time is dominant in the entire processing time. In the following, a description will be given of two types of access, sequential access and random access. However, an access located in the middle or a mixture of sequential access and random access can be dealt with by a processing method of either sequential access or random access. is there.

(5) Random Read FIG. 3 is a conceptual diagram illustrating a random read operation of the disk array. Reception of read command (FIG. 3 (1)) The host 3 generates a read host command of a small transfer length, controls the host I / F control means 32, and controls the disk array controller 1 via the host interface 31.
Issue to I / F of disk array controller 1
The control means 12 is waiting for a command in the target mode, receives the read host command, and notifies the central control means 10. The host command control unit 101 of the central control unit 10 receiving the notification receives the read host command.

Determination of transfer mode The transfer mode control unit 102 analyzes the read host command and makes a cache hit / miss determination. When the cache hits, data transfer from the data cache unit 11 to the host 3 starts. This operation is the same as the data transfer from the disk array controller 1 to the host 3 described later (FIGS. 3 (5) and (6)). When the cache misses, the transfer mode control unit 102 performs a sequential access determination. The sequential determination is performed by determining the continuity between the logical address of the previous read command and the logical address of the current read command. Here, due to random access, the sequential judgment is missed.
Then, the transfer mode control unit 102 determines that the transfer mode is “normal transfer”. In the “normal transfer”, it is not necessary to notify the host 3 and the disk device 2 of the transfer form. Therefore, the transfer mode control unit 1
02 secures a cache area for storing the data of the read host command at an appropriate address of the data cache unit 11.

Address conversion The address conversion control unit 103 specifies a disk device number for storing data of the logical address based on the logical address to the disk array stored in the read host command based on the configuration of the disk array. It is converted to the physical address of the disk device.

Issuing a disk command (FIG. 3 (2)) The disk command control unit 104 generates a read disk command for the target disk device, and issues an I / F control unit 12
Issue a read disk command to the The I / F control unit 12 receives this read disk command. The initiator / target switching control unit 121 includes an I / F
The control unit 12 is switched to the target mode. The I / F control unit 12 issues a read disk command to the disk device 2 via the host interface 31. The read disk command is transmitted as a Fiber Channel frame.

Data transfer from the disk device 2 to the disk array controller 4 (FIG. 3 (3)) When the disk device 2 receives the read disk command, the disk device 2 analyzes the read disk command, seeks the head, and waits for rotation. Then, data of the designated transfer length is read from the designated physical address. Next, the number of data frames required for all data transfer is generated and issued to the disk array controller 1 via the host interface 31. The I / F control unit 12 of the disk array controller 1 operates in the initiator mode, receives a data frame, and transfers the data frame to the data cache unit 11.

Disk command end (FIG. 3 (4)) After the transfer of the data frame is completed, the disk device 2 creates a frame storing the status and transmits it to the disk array controller 1. The I / F control means 12 of the disk array controller 1 receives the frame storing the status and notifies the central control means 10. The disk command control unit 104 of the central control means 10 confirms that the command processing has been completed normally.

Data transfer from the disk array controller to the host (FIG. 3 (5)) The host command control unit 101 instructs the I / F control unit 12 to start data transfer. The initiator / target switching control unit 121 of the I / F control unit 12 includes an I / F
The control unit 12 is switched to the target mode. I / F
The control unit 12 reads data from the data cache unit 11, creates a data frame, and transfers the data frame to the host 3 via the host interface 31.

End of read host command (FIG. 3)
(6)) I / F control means 12 of disk array controller 1
Generates a status frame when all data frames have been transferred, and transmits the status frame to the host 3. The host 3 receives the status frame, and confirms that the data transfer has been completed and the read command has been normally completed.

(6) Random Write FIG. 4 is a conceptual diagram of a random read operation of the disk array 4. Processing of write host command (FIGS. 4 (1) (2) (3)) The host 3 generates a write host command and
/ F control means 32 and the host interface 31
Is issued to the disk array controller 1 via. I / F control means 1 of disk array controller 1
2 is waiting for a command in target mode,
It receives the write host command and notifies the central control means 10. The host command control unit 101 of the central control unit 10 receiving the notification receives the write host command.
The transfer mode control unit 102 analyzes the host command,
Judgment is made as “normal transfer”, and a cache area for storing data is secured in the data cache unit 11.
The host command control unit 101 notifies the I / F control unit 12 of the address of the cache area and instructs the start of transfer. The I / F control unit 12 transmits a transfer permission frame to the host 3. The host 3 transmits a data frame. The I / F control unit 12 receives the data, stores the data in the designated area of the data cache unit 11, transmits a status frame to the host 3 when the transfer is completed, and notifies the central control unit 10 that the data transfer is completed. Notify.
The host 3 receives the status frame and confirms that the transfer has been completed and that the write host command has been normally completed.

As described above, the method of terminating the host command when data is written to the data cache unit 11 of the disk array controller 1 is called a write-back cache. Data stored in the data cache unit 11 without being written to the disk device 2 is called dirty data, and a cache storing dirty data is called a dirty cache. When the amount of dirty data is equal to or more than a specified value or when dirty data is stored for a predetermined time or more, the disk array controller 1 performs a process of writing the dirty data back to the disk device 2. This process is called a destage process.

Generation of Parity (FIGS. 4 (4) (5) (6)) Prior to destage, a parity corresponding to dirty data is generated. Here, if the dirty data is D1 (new), the new parity P0 (new) corresponding to the dirty data is D1 (new).
Is obtained by the exclusive OR of D1 (new), D1 (old) and P0 (old). Therefore, it is necessary to read D1 (old) and P0 (old) from the disk device 2. Therefore, an area for temporarily storing both data on the data cache control means 11 is allocated, and the area is read in the same manner as the data transfer from the disk device to the disk array controller in response to the read host command. The central control means 10 supplies the parity P0 (ne
Issue the generation request of w). The parity calculating means 14 generates the parity P0 (new) and generates the parity P0 (new).
In an area prepared in advance.

Destage process (disk device write process) (FIGS. 4 (7), (8), (9)) The destage process of new data and new parity is performed by the disk device to the disk array controller in response to the read host command. Basically the same as data transfer.
The difference is that the transfer direction is reversed (read becomes write), and when the disk array controller 1 issues a write disk command to the disk device 2,
The disk device 2 issues a transfer permission frame to the disk array controller 1, and the I / F control means 12 of the disk array controller 1 which has received the transfer permission frame sends a data frame to the disk device 2.

When the data writing is completed, the disk device 2 transmits a status frame to the disk array controller 1. Upon receiving this, the central control means 10 of the disk array controller 1 changes the attribute of the data cache area of the new data and the new parity from dirty to clean, and invalidates the data cache area of the old data and the old parity. Thus, the processing of the write host command is completed.

Sequential access When a miss occurs in the hit miss judgment of the cache and a hit occurs in the sequential judgment, the sequential access processing is performed. This is basically the same procedure as the random access. The difference is that, at the time of sequential reading, a plurality of read commands are issued to a plurality of disk devices 201 to 204 at the same time to collect data on the data cache unit 11 and transfer the data to the host 3. Since the data of the parity group may be arranged on the means 11, the new parity may be generated without reading the old data and the old parity from the disk device 2.

(7) Effects of the First Embodiment According to the first embodiment described above, the disk array controller 1 shares the connection interface with the host 3 and the connection interface with the disk device 2 by one host interface 31. However, since this is controlled by only one I / F control unit 12, the cost of the disk array controller 1 can be reduced even with an expensive interface such as a fiber channel.

[Second Embodiment] (Example 1 of Direct Transfer) In a second embodiment, a transfer mode called "direct transfer" which is one of the transfer modes provided in the disk array of the present invention will be described. "Direct transfer" is a transfer mode in which the host and the disk device perform data transfer without going through the disk array controller. “Direct transfer” is a transfer form that is effective mainly at the time of sequential reading.

(1) Configuration of Disk Array The disk array 1 has the same configuration as that described in the first embodiment with reference to FIGS. When performing "direct transfer", the transfer mode control means 102 of the central control means 10 of FIG. 2 is used.

(2) Configuration of Host The host 3 has the same configuration as that described in the first embodiment with reference to FIG. When performing "direct transfer", the host transfer mode control means 33 is used. The host transfer mode control unit 33 receives the transfer mode information determined and notified by the disk array controller 1, and controls the host I / F control unit 32 so that data can be exchanged using the specified transfer mode.

(3) Configuration of Disk Device The disk device 2 has the same configuration as that described in the first embodiment with reference to FIG. The disk devices 200 to 2
04 includes a disk transfer mode control unit 22, but the disk transfer mode control unit 22 is not used in the second embodiment (it is used in the third and subsequent embodiments), and therefore will not be described. Therefore, when operating only in the first embodiment “normal transfer” and the second embodiment “direct transfer example 1”, the disk transfer mode control unit 22 can be omitted.

(4) Sequential Read / Read Command Reception (FIG. 5 (1)) The host 3 generates a read host command to perform sequential access, and the host I / F control means 32
Is issued to the disk array controller 1 via the host interface 31. Here, it is assumed that the transfer length is 64 KB. The I / F control unit 12 of the disk array controller 1 waits for a command in the target mode, receives a read host command, and notifies the central control unit 10. The host command control unit 101 of the central control unit 10 receiving the notification receives the read host command.

Determination of transfer mode The transfer mode control unit 102 of the central control means 10 analyzes the read host command and makes a cache hit / miss determination. The cache misses because of sequential access. When the cache misses, the transfer mode control unit 10
2 makes a sequential access determination. here,
Since it is a sequential access, the sequential judgment hits. Then, the transfer mode control unit 102 determines the transfer mode as “direct transfer”.

Address conversion The address conversion control unit 103 specifies the disk device number for storing the data of the logical address based on the logical address of the read host command based on the configuration of the disk array, and converts it to the physical address of the disk device. I do. This conversion will be specifically described below. FIG. 6 is a diagram illustrating one parity group of a RAID4 or RAID5 disk array. Stripes 220, ..., 22
Numeral 4 indicates the respective stripes of the disk devices 200,..., 204. Steps 220 to 223 are data stripes, and stripe 224 is a parity stripe. The stripe size is 64 KB.
Transfer length of data to be sequentially accessed is 64K
However, if the address conversion results in that the data corresponds to the second half 16 KB of the stripe 220 of the disk device 200 and the first half 48 KB of the stripe 221 of the disk device 201, the data to be sequentially accessed is indicated by the hatched portion in FIG. Become.

FIG. 7 is an explanatory diagram of the relationship between a logical address and a physical address. Generally, the host memory of the host 3 uses a memory mechanism called virtual memory, and a memory block of 4 KB or the like is called a page, and necessary memory is allocated in page units. For this reason, the mapping to the actual host memory is often divided into several areas even if the logical addresses are continuous from the viewpoint of the application. Therefore, the correspondence between the host memory address, the logical address, and the physical address of the disk array 4 is managed. Then, according to the correspondence, the host I / F control means 32 transfers the received data to an appropriate host memory address. Such a mechanism is called Scatter / Gather (S / G), a list indicating the relationship between the logical address and the memory address is called an S / G list, and when a host command is issued, the host 3 generates the list. , To the host I / F control means 32. According to this list, the host I / F control means 32
Performs data transfer.

FIG. 8 shows an example of the address conversion list 1030 created by the address conversion control unit 103. The address translation list 1030 indicates that data of a certain transfer length (for example, 16 KB) from a certain logical address (for example, LA0) starts from a specific physical address (for example, PA1) of a specific disk device (for example, the disk device 200). Is shown.

Transfer of direct transfer message (FIG. 5)
(2), (3)) Returning to FIG. 5, next, the host command control unit 101 creates a direct transfer message to the host 3, and
It is issued to the F control means 12. The direct transfer message stores an identifier indicating that the message is a direct transfer message and the address conversion list 1030. I
The / F control means 12 creates a message frame, sends the message frame to the host 3, transfers the status frame to the host 3, and ends the read host command once.

Generation of Direct Transfer S / G List The host I / F control means 32 of the host 3 receives the message frame and further receives the status frame, and temporarily terminates the read host command once. . The host transfer mode control means 33 analyzes the direct transfer message stored in the message frame and recognizes that the transfer mode is "direct transfer". Then, the address conversion list 1030 stored in the direct transfer message is compared with the S / G list, the relationship between the physical address of each disk device and the memory transfer destination address is examined, and each disk device 200, 20 is checked.
A direct transfer S / G list corresponding to No. 1 is generated.
FIG. 9 illustrates a direct transfer S / G list. The direct transfer S / G list 3300 is stored in the disk device 200
And the direct transfer S / G list 3301 corresponds to the disk device 201.

Execution of direct transfer (FIGS. 5 (4), (5),
(6)) Next, the host transfer mode control unit 33 creates a disk command for each disk device using the address conversion list 1030, and issues it to the host I / F control unit 32. The host I / F control unit 32 issues a disk command to each of the disk devices 200 and 201 via the host interface 31. Disk devices 200 and 300
Performs independent seek and rotation waits, and starts data transfer from the one prepared earlier. Host I / F
The control unit 32 receives the data frame, confirms the number of the transfer source disk device from the header of the frame, and performs data transfer to the host memory according to the direct transfer S / G list for each disk device. In this example, when data is sent from the disk device 200, the first 8 KB is stored in the memory address MA0 of the host memory, and the next 8 KB is stored in the memory address MA1. When data is sent from the disk device 201, the first 24 KB is stored in the memory address (MA1 + 8K).
B), and the next 24 KB is stored in the memory address MA2. At this time, it is not necessary to be aware of the physical addresses of the disk devices 200 and 201, and the data may be stored according to the direct transfer S / G list in the order of the transmitted data. When the data transfer from all the disk devices is completed and the status frame is received, the disk command ends normally.

Termination of host command When all disk commands have been completed normally, the data transfer is completed. Therefore, the host I / F control means 32 normally terminates the previously provisionally terminated host command and returns this request. Return the normal end status to the issued application and end the process.

(5) Processing Other than Sequential Read Although the processing of sequential read has been described above, direct transfer can be performed in a manner other than sequential read (for example, random read) in the same manner as described above.

In the case of the direct transfer described above, since data cannot be cached in the data cache means 11 in the disk array controller 1, it is impossible to realize high-speed access by a cache hit. However, when it is known that the data is never used (there is no need to cache), or when the memory capacity of the data cache unit 11 is small (a cache hit in the data cache unit 11 cannot be expected). Or the capacity of the disk device cache provided in the host 3 is large (there is no need to use the data cache unit 11).
In some cases, the above direct transfer is also effective. In a fourth embodiment to be described later, direct transfer is performed simultaneously with caching in the disk array controller 1.

(6) Effects of the Second Embodiment According to the second embodiment described above, at the time of sequential reading, data read from the disk device 2 is transmitted directly to the host 3 without passing through the disk array controller 1. Since the transfer is performed, the data transfer can be realized by using the transfer speed of the host interface 31 to the maximum. Further, the host I / F and the disk device I / F become one, and the cost can be reduced. Further, the same I / F is used twice as the transfer from the disk device 2 to the disk array controller 1 and the transfer from the disk array controller 1 to the host 3 as in the "normal transfer" of the first embodiment. Although there is a decrease in performance in this case, high-speed transfer can be realized without causing such a decrease in performance. That is, the processing time required for data buffering in which data is once read into the data cache unit 11 of the disk array controller 1 can be reduced, and the access response time can be reduced.

Further, the data from the disk device 2 is
Since the data does not pass through the data bus inside the disk array controller 1, there is no need to increase the bandwidth of the data bus and the cache memory of the disk array controller 1. As a result, the bus bit width, the frequency, the memory bit width, and the number of interleaves can be reduced, and the disk array controller 1 can be easily developed. 1 can be significantly reduced.

Further, since there is almost no cache hit at the time of the sequential access, it is possible to prevent the cache hit rate from decreasing due to useless use of the data cache in the conventional disk array. Access speed can be increased.

Further, high speed can be realized by direct transfer while using the same disk device as the conventional one, and the transition from the conventional system is easy.

[Third Embodiment] (Example 2 of Direct Transfer) In the third embodiment, "direct transfer" different from the second embodiment will be described. The "direct transfer" of the third embodiment is also a transfer mode effective mainly at the time of sequential reading, as in the second embodiment. (1) Configuration of Disk Array This is the same as the second embodiment. (2) Configuration of Host This is the same as the second embodiment. (3) Configuration of Disk Device This is the same as the second embodiment. In the third embodiment, a disk transfer mode control unit 22 that receives the transfer mode determined by the disk array controller 1 and determines the transfer mode based on the received transfer mode is used.

(4) Sequential Read / Read Command Reception (FIG. 10 (1)) The host 3 generates a read host command to perform sequential access, and the host I / F control unit 32
Is issued to the disk array controller 1 via the host interface 31. Here, it is assumed that the transfer length is 64 KB. The I / F control unit 12 of the disk array controller 1 waits for a command in the target mode, receives a read host command, and notifies the central control unit 10. The host command control unit 101 of the central control unit 10 receiving the notification receives the read host command.

Determination of Transfer Mode The transfer mode control unit 102 of the central control means 10 analyzes the read host command and makes a cache hit / miss determination. The cache misses because of sequential access. When the cache misses, the transfer mode control unit 10
2 makes a sequential access determination. here,
Since it is a sequential access, the sequential judgment hits. Then, the transfer mode control unit 102 determines the transfer mode as “direct transfer”.

Address conversion The address conversion control unit 103 specifies the disk device number for storing the data of the logical address based on the logical address of the read host command based on the configuration of the disk array, and converts it to the physical address of the disk device. I do. Here, it is assumed that the address conversion control unit 103 has generated the address conversion list 1030 shown in FIG.

Transfer of direct transfer message (FIG. 1)
0 (2)) Returning to FIG. 10, the host command control unit 101 creates a direct transfer message to the host 3 and
/ F control means 12. The I / F control means 12 includes:
A message frame is created, and the message frame is sent to the host 3. However, unlike the second embodiment, at this point, no status frame is transmitted.

Generation of Direct Transfer S / G List The host I / F control means 32 of the host 3 receives the message frame. The host transfer mode control means 33 analyzes the direct transfer message stored in the received message frame and recognizes that the transfer mode is "direct transfer". Then, similarly to the second embodiment, the direct transfer S / G lists 3300 and 3301 are generated, and the process waits for data transfer from the disk device 2.

Issuance of a copy command to the disk device (FIG. 10 (3)) On the other hand, in the disk array controller 1, the disk command control section 104 of the central control means 10 determines the disk device 2 based on the address conversion list 1030. A copy command for instructing the host 3 to transfer data of the specified length from the specified address is generated and issued to the I / F control unit 12. This copy command is distinguished from a read command for reading data from the disk device 2 to the disk array controller 1. The I / F control unit 12 issues a copy command to each of the disk devices 200 and 201.

Execution of Direct Transfer by Copy Command (FIGS. 10 (4) and 10 (5)) In the disk devices 200 and 201, the respective disk I / F control means 21 receives the copy command. The disk transfer mode control unit 22 confirms that the direct transfer by the copy command is performed. Then, the disk devices 200 and 201 independently perform seek and rotation wait, and start data transfer to the host 3 from the one prepared earlier. The host I / F control means 32 of the host 3 receives the data frame, checks the number of the transfer source disk device from the header of the data frame,
Data is transferred to the host memory according to the direct transfer S / G lists 3300 and 3301 for each disk device. When the data transfer from all the disk devices is completed, the disk devices 200 and 201 create a status frame and send it to the disk array controller 1. When the I / F control unit 12 of the disk array controller 1 receives the status frame, the copy command ends normally.

Termination of host command When all copy commands are completed normally, the host command control unit 101 of the disk array controller 1
Creates a status for the read host command. The I / F control unit 12 creates a status frame and sends it to the host 3. The host 3 receives this status frame, recognizes that the host command has ended normally, returns a normal end status to the application that issued this request, and ends the processing.

(5) Effects of the Third Embodiment According to the third embodiment described above, the same effects as those of the second embodiment can be obtained.

Fourth Embodiment (Example of Multi-Target Direct Transfer) In a fourth embodiment, a transfer mode called “multi-target direct transfer” which is one of the transfer modes provided in the disk array of the present invention will be described. . The "multi-target direct transfer" is a transfer form mainly used for random read, and can solve both the consumption of the interface bandwidth and the delay of the response time as in the second and third embodiments, and the speedup by the cache. Is also possible. (1) Configuration of Disk Array This is the same as the third embodiment. (2) Configuration of Host This is the same as the third embodiment. (3) Configuration of Disk Device This is the same as the third embodiment.

(4) Random Read / Receive Read Command (FIG. 11 (1)) As shown in FIG. 11, the host 3 generates a read host command to perform read access, and controls the host interface control means 32. Then, it is issued to the disk array controller 1 via the host interface 31. I / F control means 1 of disk array controller 1
2 is waiting for a command in the target mode, receiving a read host command, and
Notify. The host command control unit 101 of the central control unit 10 receiving the notification receives the read host command.

Determination of Transfer Mode The transfer mode control unit 102 analyzes a read host command and determines a cache hit / miss. Here, it is assumed that a cache miss has occurred. Then, the transfer mode control unit 102 performs a sequential access determination next. Here, since it is a random access, a mishit occurs.
Therefore, the transfer mode control unit 102 determines the transfer mode as “multi-target direct transfer”.

Address Conversion Next, the address conversion control unit 103 obtains a disk device number and a physical address from the logical address of the read host command based on the configuration of the disk array, and sends a multi-target read disk command to the target disk device. Generate. The multi-target read disk command is a command for instructing the data read from the disk device 2 to be simultaneously transferred to both the disk array controller 1 and the host 3, and can have an initiator ID and a plurality of target IDs. .

Transfer of direct transfer message (FIG. 1)
1 (2)) Next, the host command control unit 101 creates a direct transfer message to the host 3 and issues it to the I / F control unit 12. The I / F control unit 12 creates a message frame and sends it to the host 3.

Generation of Direct Transfer S / G List The host I / F control means 32 of the host 3 receives the message frame. The host transfer mode control means 33 analyzes the direct transfer message stored in the received message frame, and recognizes that the transfer mode is “multi-target direct transfer”. Then, it generates a direct transfer S / G list and waits for data transfer from the disk device 2.

Issuance of Multi-Target Read Disk Command (FIG. 11C) On the other hand, the disk command control unit 104 issues a multi-target read disk command to the I / F control unit 12. The I / F control unit 12 issues a command frame to the disk device 2 via the host interface 31.

Data transfer from the disk device to the disk array controller and the host (FIG. 11 (4)) The disk I / F control means 21 of the disk device 2 receives the command frame. Disk transfer mode control means 2
2 analyzes the command, recognizes that the command is a multi-target read disk command, and determines to transfer data to both the disk array controller 1 and the host 3. Then, seek the head and wait for rotation,
The data of the designated transfer length is read from the target physical address. Next, the disk I / F control unit 21 generates the number of data frames having two target IDs of the disk array controller 1 and the host 3 required for all data transfer, and issues the data frames via the host interface 31. I / F control means 1 of disk array controller 1
2 and the host I / F control means 32 of the host 3 receive the same data frame. The I / F control means 12 of the disk array controller 1 stores data in the area of the data cache means 11 designated in advance. Further, the host I / F control means 32 of the host 3 stores data in the host memory according to the direct S / G list.

End of Disk Command (FIG. 11 (5)) After the end of the transfer, the disk I / F control means 21 of the disk device 2 creates a frame storing the status and sends it to the disk array controller 1. The I / F control means 12 of the disk array controller 1 receives this and notifies the central control means 10. The disk command control unit 104 of the central control means 10 confirms that the command processing has been completed normally.

End of host command (FIG. 11 (6)) I / F control means 12 of disk array controller 1
Generates a status frame and sends it to the host 3. The host 3 receives the status frame, and confirms that the data transfer has been completed and the read command has been normally completed.

(5) Sequential Write Receiving Write Command (FIG. 12 (1)) As shown in FIG. 12, the host 3 generates a write host command to perform write access, and controls the host interface control means 32. Then, it is issued to the disk array controller 1 via the host interface 31. I / F control means 1 of disk array controller 1
2 is waiting for a command in the target mode, receiving a write host command, and
Notify. The host command control unit 101 of the central control unit 10 receiving the notification receives the write host command.

Determination of transfer mode The transfer mode control unit 102 analyzes the write host command, recognizes that all the data of the parity group has been written, and determines that the transfer is “multi-target direct transfer”.

Address Conversion Next, the address conversion control unit 103 obtains a disk device number and a physical address from the logical address of the write host command based on the configuration of the disk array, and sends a multi-target write disk command to the target disk device. Generate. The multi-target write disk command is a command for instructing the host 3 to simultaneously transfer data to be written to both the disk device 2 and the disk array controller 1, and can have an initiator ID and a plurality of target IDs. .

Transfer of direct transfer message (FIG. 1)
2 (2)) Next, the host command control unit 101 creates a direct transfer message to the host 3 and issues it to the I / F control unit 12. The I / F control unit 12 creates a message frame and sends it to the host 3.

Generation of Direct Transfer S / G List The host I / F control means 32 of the host 3 receives the message frame. The host transfer mode control means 33 analyzes the direct transfer message stored in the received message frame, and recognizes that the transfer mode is “multi-target direct transfer”. Then, a direct transfer S / G list is generated.

Issuance of a multi-target write disk command (FIG. 12 (3)) On the other hand, the disk command control unit 104 issues a multi-target write disk command to the I / F control unit 12. The I / F control unit 12 issues a command frame to the disk device 2 via the host interface 31. Disk I / F control means 21 of disk device 2
Receives a command frame. The disk transfer mode control unit 22 analyzes the command and recognizes that the command is a multi-target write disk command.

Data transfer from host to disk device and disk array controller (FIG. 12 (4)) The host 3 transfers data to both the disk device 2 and the disk array controller 1. The disk array controller 1 stores data in a cache. The disk device 2 stores data.

End of disk command (FIG. 12 (5)) After the end of data storage, the disk I / F of the disk device 2
The control unit 21 creates a frame in which the status is stored, and transmits the frame to the disk array controller 1. The I / F control means 12 of the disk array controller 1 receives this and notifies the central control means 10. The disk command control unit 104 of the central control means 10 confirms that the command processing has been completed normally.

End of host command (FIG. 12 (6)) I / F control means 12 of disk array controller 1
Generates a status frame and sends it to the host 3. The host 3 receives the status frame, and confirms that the data transfer has been completed and the write command has been normally completed.

Write of Parity (FIGS. 12 (7) and (8)) If all data of the parity group is available in the cache, the disk array controller 1 generates a parity and writes it to the disk device 2. On the other hand, if all the data of the parity group are not available, the disk array controller 1 reads the old data and the old parity from the disk device 2, generates a new parity from the new data, the old data and the old parity, and generates the new parity. Write to the disk device 2.

End of disk command (FIG. 12 (9)) After the end of parity storage, the disk I / O
The F control unit 21 creates a frame in which the status is stored, and transmits the frame to the disk array controller 1. The I / F control means 12 of the disk array controller 1 receives this and notifies the central control means 10. The disk command control unit 104 of the central control means 10 confirms that the command processing has been completed normally.

(6) Processing other than random read and sequential write In the case of random write and sequential read, multi-target direct transfer can be performed in the same manner as described above.

(7) Effects of the Fourth Embodiment According to the fourth embodiment described above, since all of the host 3, the disk array controller 1, and the disk device 2 are connected to the same host interface 31, one operation is performed. Can be simultaneously transferred to both the host 3 and the disk array controller 1 by the transfer from the disk device 2 and can be simultaneously transferred to both the disk device 2 and the disk array controller 1 by the transfer from the host 3 once. The traffic of the host interface 31 can be reduced. That is, the same effect as in the second embodiment can be realized in all access types. Further, data can be cached in the data cache unit 11 of the disk array controller 1. In particular, it effectively functions in the write operation of the RALD3 in which data is always written in parity group units.

Fifth Embodiment (Dual Controller Configuration) In a fifth embodiment, two identical disk array controllers are provided in the first to fourth embodiments, each having the same host interface and the same disk device. I
/ F (and disk device) are shared. Such a configuration is called a dual controller configuration. In the dual controller configuration, the bus inside the controller, M
It is possible to withstand the respective failures of the components such as the PU and the cache memory.

When a dual controller configuration is applied to the first embodiment or the fourth embodiment, when data is written from the host 3, one disk array controller writes data to the cache and the other disk array controller simultaneously writes data to the cache. Also write
Duplicate data. At this time, after one disk array controller receives the data, that disk array controller may copy the data to the other disk array controller, but the data is transferred from the host 3 to both disk array controllers simultaneously by the multi-target transfer. Is preferably transferred. This allows
Copy processing between disk array controllers can be reduced.

Sixth Embodiment (Separation of Interface) In the first to fifth embodiments, the I / F control means for communicating with the host 3 and the I / F control means for communicating with the disk device 2 And one I / F control means 1
2 are shared by the two host interfaces, but both are separated into separate I / F control means, and both I / F control means are shared by the same host interface 3.
1 may be connected. In this case, although the cost of the I / F control means is doubled, since the initiator / target can be used without switching, the control is facilitated and the performance is improved.

[Addition] The transfer mode of the present invention is not limited to the combination with the access type described in the first to fourth embodiments, but may be any type of access (even if the access type is not described above). Good) can be used in combination.

[0106]

According to the disk array control method and the disk array control device of the present invention, the following effects can be obtained. (1) Even if a high-speed interface is adopted, the host interface and the disk device
The cost can be reduced because it is shared by two interfaces. (2) By using direct transfer, data can be directly transferred between the disk device and the host without going through the disk array controller, so that the overhead time required for buffering can be reduced and the response time can be reduced. Performance can be improved, the performance of the high-speed interface can be maximized, and the transfer speed inside the disk array controller can be kept low. Can be planned. (3) By using the multi-target direct transfer, it is possible to improve the above-described effects of the direct transfer and the responsiveness of the cache.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of a computer system according to an embodiment of the present invention.

FIG. 2 is an internal configuration diagram of a central control unit in the disk array controller according to one embodiment of the present invention.

FIG. 3 is an explanatory diagram of an operation of “normal transfer” in random read according to the first embodiment of the present invention.

FIG. 4 is an explanatory diagram of an operation of “normal transfer” in random write according to the first embodiment of the present invention.

FIG. 5 is an explanatory diagram of an operation of “direct transfer” in a sequential read according to the second embodiment of the present invention.

FIG. 6 is a conceptual diagram of read data for explaining a second embodiment of the present invention.

FIG. 7 is an explanatory diagram of a relationship between a logical address and a physical address for explaining a second embodiment of the present invention.

FIG. 8 is a configuration diagram of an address conversion list for explaining a second embodiment of the present invention.

FIG. 9 is a configuration diagram of a direct transfer S / G list for explaining a second embodiment of the present invention.

FIG. 10 is an explanatory diagram of an operation of “direct transfer” in the sequential read according to the third embodiment of the present invention.

FIG. 11 is an explanatory diagram of an operation of “multi-target direct transfer” in random read according to the fourth embodiment of the present invention.

FIG. 12 is an explanatory diagram of an operation of “multi-target direct transfer” in the sequential write according to the fourth embodiment of the present invention.

FIG. 13 is an explanatory diagram of a data structure of a conventional RAID type disk array.

FIG. 14 is a configuration diagram of an example of a conventional SCSI disk array.

FIG. 15 is a configuration diagram of an example of a conventional FC disk array.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 Disk array controller 2 Disk device 3 Host 4 Disk array 10 Central control means 11 Data cache means 12 I / F control means 14 Parity calculation means 21 Disk I / F control means 22 Disk transfer mode control means 31 Host interface 32 Host I / F control unit 33 host transfer mode control unit 100 computer system 101 host command control unit 102 transfer mode control unit 103 address conversion control unit 104 disk command control unit 121 initiator / target switching control unit 200 to 204 disk device

 ──────────────────────────────────────────────────続 き Continuing from the front page (72) Inventor Ikuya Yagisawa 1099 Ozenji Temple, Aso-ku, Kawasaki City, Kanagawa Prefecture Inside Hitachi, Ltd.System Development Laboratory Co., Ltd. (72) Inventor Jun Matsumoto 1099 Ozenji Temple, Aso-ku, Kawasaki City, Kanagawa Prefecture, Japan Incorporated Hitachi System Development Laboratory (72) Kenichi Takamoto 2880 Kozu, Kozu, Odawara City, Kanagawa Prefecture Hitachi Storage Systems Division (72) Inventor Toshiaki Tsuboi 5-22-1, Josuihonmachi, Kodaira-shi, Tokyo F-term in Hitachi Super LSI Systems Co., Ltd. 5B014 EB04 GD22 GD23 GD24 5B065 BA01 CA30

Claims (5)

[Claims] 1. A host, a disk array controller for controlling a plurality of disk devices to logically operate as one or more disk array devices when viewed from the host, and
The plurality of disk devices are connected to one host interface, and communication between the disk array controller and the host and communication between the disk array controller and the plurality of disk devices are performed via one host interface. A disk array control method, characterized in that: 2. A host interface connected to a host and a plurality of disk devices, for controlling the plurality of disk devices to logically operate as one or more disk array devices as viewed from the host. An I / F control unit for controlling a host interface, a host command control unit for performing processing such as receiving a command from a host, a host device interpreting a host command and communicating with a host in accordance with the result. A transfer mode control means for determining a transfer path and a transfer mode between the disk array controller and the plurality of disk devices; and a host command instructed based on the determined transfer path and transfer mode and the configuration of the disk array. Disk device corresponding to address converted to disk device address Address conversion control means for generating a disk command, the disk array controller being characterized in that a disk command control means for performing processing such as issuing a disk command to the disk device. 3. The disk array control device according to claim 2, wherein when the host command is a read command, the transfer mode control means transmits the data from the disk device to the disk array control device, and then transfers the data to the disk array control device. Normal transfer, in which data is transferred from the host to the host, can be selected as the transfer mode, and when the host command is a write, the data is transferred from the host to the disk array controller, and then the data is transferred from the disk array controller to the disk device. A disk array control device, wherein "normal transfer for transfer" can be selected as a transfer mode. 4. The disk array control device according to claim 2, wherein said transfer mode control means comprises:
When the host command is a read, it is possible to select "direct transfer in which data is directly transferred from the disk device to the host without passing through the disk array controller" as a transfer mode, and when the host command is a write,
A disk array control device characterized in that at least one of a direct transfer that directly transfers data from a host to a disk device without passing through a disk array control device can be selected as a transfer mode. 5. The disk array control device according to claim 2, wherein the transfer mode control means reads from the disk device to the disk array control device when the host command is read and a cache miss occurs. Multi-target direct transfer, which transfers data to both the host and the host, can be selected as the transfer mode, and when the host command is a write, the multi-target direct transfer that transfers data from the host to both the disk array controller and the disk device A disk array control device wherein at least one of a direct transfer mode and a direct transfer mode can be selected.