Storage controlling unit

The present application is a continuation application of application Ser. No. 11/106,536, filed Apr. 15, 2005; which claims priority from Japanese application P2005-036114 filed on Feb. 14, 2005, the content of which is hereby incorporated by reference into this application.

This invention relates to a storage controller for storing data in one or plural disk devices, in particular, to a storage controller capable of changing a system configuration with scalability.

Each year sees an increase in digital data to be stored at a corporate, governmental, municipal, or even personal level, and an increase in need for a larger capacity of a storage system. There are also increasing numbers of users and hosts that access digital data. Herein, the hosts access the digital data by communicating with data input/output devices such as a monitoring camera image controller, various personal authentication devices, authentication management servers on the Internet, sensor systems used for a traffic information system, and the like.

To meet such demands, it is necessary to structure a storage system that has the larger storage capacity and can handle the increasing number of accesses. However, as the demands increase as described above, it is difficult to make future projections for expansion while narrowing and pinpointing its prediction range. Therefore, vendors who introduce a system build the initial system based on prediction on the scale of a “just-in-case” system (provided with more than enough margins even for unlikely events). In other words, vendors introduce devices having resources with a size larger than that for the current use, or devices to which systems and the resources can be easily added later.

As represented by a large-scale disk array system, a conventional storage system presupposes a large-scale system configuration, and includes basic components required when setting up the large-scale system configuration or equipments to be required in the future. Examples thereof include a power source, a battery, a back plane having a number of slots for a large-scale system configuration, a shared memory blade for the large-scale system configuration, and a network (switch) blade.

Vendors of storage systems provide a plurality of models. For example, the vendors provide three models including small-through small/medium-scale devices, small/medium-through medium/large-scale devices, and medium/large-through large-scale devices. An example thereof is disclosed in “Symmetrix DMX Architecture Production description Guide”, EMC Corporation, browsed online on the Internet at <URL: http://www.emc.com/products/systems/pdf/C1011_emc_symm_dmx_pdg_ldv. pdf>in April 2004.

Immediately after the introduction of the storage system, the minimum necessary configuration may be sufficient for a customer. However, the large-scale system configuration becomes necessary when the future projections for expansion of the system are taken into account.

A user can decide the scale of the storage system to be initially introduced among the above models to reduce cost for initial introduction of the storage controller into a system when the user\'s future projections for expansion are within the range of scalability of the model. On the other hand, when desired expansion of the device exceeds the range of scalability of the model decided by the user, it becomes necessary to replace the entire device or purchase an additional device, which increases cost required therefore.

What is most desirable for a user is to realize cost commensurate with the scale (small scale or large scale) of a storage system and to be allowed to expand the scale thereof between the small- and large-scales. However, with the reduced cost, it is difficult to provide the storage system with a sufficient scalability required therefore.

Discussion will be made herein as to ensuring sufficient scalability in a prior-art storage array device. In this case, the storage controller of the storage array device needs to have in advance such a mechanism (for example, an enhancement interface; hereinafter, referred to as “enhancement function”) as to allow addition of various devices. However, the storage array device has a serious demand for reduced cost, and when an enhancement mechanism is merely introduced into the storage array device, cost for initial introduction becomes relatively high for the user having no clear future projections for expansion.

This issue will be described in detail. As an example, consideration is given to the prior-art storage array device including the storage controller blade and switch connection blade with shared memory unit.

For example, in the small-scale system configuration, the storage array device includes four storage controller blades and two switch connection blades with a shared memory. In this case, the system scale of the device becomes quite smaller.

In contrast, a case is assumed where the device is changed from the small-scale into a large-scale system configuration. The large-scale system includes 16 storage controller blades and four switch connection blades with a shared memory. The device is mounted with connection among many blades depending on its scale.

The type of mounting the blades differs between the prior-art small-scale and large-scale systems, and the connection between the blades basically has no commonality. When the device is formed into a small size by using a small number of blades limiting the scalability of the system, the relationships between the blades do not match, which does not allow the enhancement into the large-scale system configuration.

Accordingly, even when the small-scale model is initially introduced, the initial introduction cost is invested in vain upon the transition to the large-scale system. In other words, the user needs to invest cost for purchasing a model having a scalability aiming at a large scale, or excess cost more than the above cost, from the beginning.

It is also effective for users and vendors who introduce a system to provide a device having a scale desired by a user at necessary, sufficient cost. However, this point of view is not taken into account in prior arts.

This invention has been made in view of the above-mentioned problems, and it is therefore an object of this invention to provide a storage controller with sufficient scalability.

In order to achieve the above objects, this invention provides a storage controller for controlling data access made between a host computer and a disk device, including one or more storage controller blades and a mutual network system that connects the storage controller blades to one another, in which the storage controller blade each includes: interface units that each connect to one of the host computer and the disk device; a processor unit that controls a configuration of the storage controller and the data access; a memory unit that stores a data cache and configuration information on the interface unit and the processor unit; and a mutual connection unit that connects the interface units, the processor unit, and the memory unit to one another, and connects to the storage controller blades. The processor unit recognizes a form of connection to another storage controller blade over the mutual network system, and the connection path to another storage controller blade is set in the mutual connection unit based on the recognized form of connection.