TWI231442B - Virtual storage layer approach for dynamically associating computer storage with processing hosts - Google Patents

Abstract

A method and apparatus for selectively logically adding storage to a host features dynamically mapping one or more disk volumes to the host using a storage virtualization layer, without affecting an operating system of the host or its configuration. Storage devices participate in storage area networks and are coupled to gateways. A boot port of the host is coupled to a direct-attached storage network that includes a switching fabric. When a host needs storage to participate in a virtual server farm, software elements allocate one or more volumes or concatenated volumes of disk storage, and command the gateways and switches in the storage networks to logically and physically connect the host to the allocated volumes. As a result, the host acquires access to storage without modification to a configuration of the host, and a real-world virtual server farm or data center may be created and deployed substantially instantly.

Description

1231442 A7 ____ B7___ V. Description of the invention (1) Cross-reference to related applications The present invention is filed on February 11, 2000, with application serial number 0 9/5 02, 1 70, and entitled "Part of Extensible Computing System π" Continuing, the inventor is Ashar Aziz et al. Its domestic priority is declared under 35 USC § 120. This application is related to the construction of the file on September 20, 2000, application serial number 09 / 630,440, entitled "Used to control a "Extensible computing system method and device", the inventor is Ashar Aziz et al., The domestic priority is June 20, 2000, which is 35 USC § 119 of the previous application serial number 60/2 1 2,936 file, title Inventors for "computation gate structure" are Ashar Aziz, Martin Patterson, Thomas Markson, etc., and the previous application serial number 60/2 1 2,873 file filed on June 20, 2000, entitled "Storage Structure and production ", and the inventors are Ashar Aziz, Martin Patterson, Thomas Markson and others. Scope of the invention The present invention relates generally to data processing. More specifically, the present invention relates to a method for dynamically linking a computer storage to a virtual storage layer of a processing host. Background of the Invention Data processing users require a flexible, extensible method to quickly generate and deploy complex computer systems and data centers, including a plurality of servers, one or more sets of load balancers, firewalls, and Other network components. The method used to generate such a system is illustrated in the file of pending application number 09 / 502,170, which was created on February 11, 2000, and titled `` Extensible Computing System ''. The inventor was Ashar Aziz et al. 4 The paper size is applicable to the Chinese National Standard (CNS) A4 specification (21GX297 mm) " I TIA 螓 丨 丨 (Please read the precautions on the back before filling this page) Order-, the wisdom of the Ministry of Economy Printed by the Consumer Cooperative of the Property Bureau 1231442 A7 B7 V. Description of the invention (2) The overall disclosure and cooperation are used for reference herein. Aziz et al. Disclose a method and apparatus for selecting components to configure a particular computer system from large, extensible computing components. Therefore, when needed, a virtual server farm or other data center can be generated, configured, and connected to perform real-time virtual work on a wide area computer network. Although the method and system disclosed by Aziz et al. Are highly effective and flexible, users and managers of extensible computing components, and the virtual server farm generated by using it, can be used to connect storage elements to Improved approaches to processors in virtual server farms benefit. For example, an improved method by Aziz et al. Is to dynamically connect a specific amount of computer data storage to a specific processor at a specific time period, and to separate the storage from the processor when the storage is no longer needed. Using a set of familiar online services, "Rackspace.com", users can choose a set of server platforms, configure them with the required combination of disk storage, tape backup, and some software choice, and Then use the configured server on a monthly basis. However, this service can only be used to configure a single server computer. Further, the system does not provide a way to dynamically or automatically A method to increase and remove the required number of storages from the server.

The example disclosed by Ashar et al. Shows that the method of starting, using, and releasing a virtual server farm is a specific storage element that can be used for the benefit of the first enterprise at a specific time, and can be used for the entire later The benefits of different secondary companies are used. Therefore, a storage element can be effectively used to successfully store the private secrets of two unrelated companies. 5 The paper size applies to the Chinese National Standard (CNS) A4 specification (210 × 297 mm) (Please read the precautions on the back before filling out This I),? Τ Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 ^ _____ B7 V. Description of the Invention (3) Information. Therefore, strong security is needed to ensure that when a set of storage elements is reassigned to a virtual server farm of a different enterprise, the enterprise has no way to use or access the data recorded on the storage element by the previous enterprise. Previous methods failed to take into account this critical security issue. A related problem is that companies are generally given basic passwords to access their virtual server farms, so the companies can monitor the virtual server farms, load data on them, and so on. Moreover, owners or operators of data centers that include one or more virtual server farms generally do not monitor the activities of enterprise users on their designated servers. Such users can use any software they wish on their servers, and they do not need to inform the owner or operator of the data center when the server changes. Virtual server farms contain processing hosts that are considered unreliable, however they must use absolutely complete storage. Therefore, it is necessary to ensure that such enterprises cannot access storage elements and cannot gain access to storage elements that are not part of their virtual server farm. Another problem is to improve security. Storage elements associated with processors in a virtual server farm should be selectively placed in a central location. It needs to have a single management location and prevent the use of disk storage in the actual area of the processor making the virtual server farm in order to prevent unauthorized tampering by enterprise users with such storage. Another problem is that enterprise users of virtual server farms want full control of the operating system and execution of business-friendly applications in the virtual server farm. In the past, to add storage to the processing host, you need to modify the operating system configuration file after the host is turned on again, so that its operating system is 6 paper standards applicable to the Chinese National Standard (CNS) Α4 specification (210 x 297 mm) I τινΊ4ι— (Please read the notes on the back before filling out this page) Order # · Printed by the Employees ’Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 B7 V. Invention Description (4) Printed by the Consumers’ Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs Be aware of the changed memory configuration. However, business users want to define a specific disk image that contains the operating system, applications, and support configuration files and related data. It is placed in a virtual server farm and is executed for business benefits. It has Security while remaining intact even when the storage is added or removed. Therefore, there is a need to provide a method to selectively attach and detach storage with a virtual server farm without modifying or interrupting a disk image or operating system that is then used by a particular enterprise, and without requiring the host to reboot. Another issue in this article is the backup copy of the information on manufacturing storage elements. For data center operators, moving between the majority of data storage locations in order to achieve periodic data backups stored in the data storage locations can be difficult and time consuming. There is therefore a need for a method to provide storage that can be optionally attached and detached from the virtual server farm and that backups can also be replicated in a practical manner. A specialization problem in this article arises from the use of a central array fiber-optic channel (FC) storage element connected to a processor booted from a small computer system interface (SCSI) port. A host or server may require storage using one or more FC disk storage arrays. The FC disk storage arrays can be placed on a central location, or any other location that can be addressed via a communications network. Above. The host is configured in the firmware or operating system to always boot from a disk target via the SCSI port. However, in the past, there was no way to boot the processor to boot from a specified disk logical unit (LUN), a volume placed across a network's central disk array, or a connected volume. Therefore, a method is required to map an arbitrary FC element to enter (please read the precautions on the back before filling this page). Ordering · This paper size applies to China National Standard (CNS) A4 (210X297 mm) 1231442 A7 ______B7 5 (5) The SCSI address space of the processor so that the processor can boot from the FC component. (Please read the notes on the back before filling out this page) According to the above, within the scope of this method, a method is clearly needed 'in order to quickly and automatically link a set of data when the virtual server farm needs storage The storage unit is separated from the virtual server farm, and the data storage unit is separated from the virtual server farm when the virtual server no longer needs the data storage unit. It requires a specific way to connect the storage to the virtual server farm in a secure manner. There is also a need for a method to selectively link storage to a virtual server farm without having to modify or adversely affect the operating system or the enterprise-specific applications that will be executed in this virtual server farm for its benefit. Summary of the invention The above-mentioned requirements and other needs achieved by the employee's consumer cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs will be more apparent from the following description. One of its arguments includes using a virtual memory layer to dynamically connect computer storage The method with the host. A connection storage requirement is received at a virtual storage layer, which is coupled to a plurality of storage units and to one or more sets of hosts. The one or more sets of hosts may not have currently designated storage, or may have currently designated storage, but require additional storage. The request identifies a specific set of hosts and the number of storage requested. By reconfiguring the virtual storage layer to logically combine logical units to the identified host, one or more sets of logical units are mapped to the identified host among storage units having the required number of memories. In this article, "storage unit" indicates a logic within a single disk array. 8 This paper size applies to the Chinese National Standard (CNS) A4 specification (210X297 mm) 1231442 A7 ___B7 5. Description of the invention (6) Unit (for example, LUN), or storage encompassed by a number of components, including disk drives, tape drives, memory caches, CDs, DVDs, etc., or a number of logical or physical units or sub-units within such components The unit's LUN. According to one characteristic, one or more sets of logical units are mapped to a standard boot port of the identified host by reconfiguring the virtual memory layer to logically combine the logical unit to the boot port of the identified host. In another aspect, the present invention provides a method for selectively logically coupling storage to a processing host. In one embodiment, the argument of the present invention is to use the storage virtualization layer to map one or more sets of disk logical units to the host without affecting the host's operating system or its configuration. The storage element participates in the storage area network and is coupled to the gateway. When the host needs storage to participate in the virtual server farm, the software component places the volume or connected volume of one or more sets of disk storage, specifies the volume or connected volume to a logical unit (LUN), and orders the storage network Gateways and switches on the way to logically and physically connect the host to the designated LUN. As a result, the host gains access to the storage without having to modify the host's configuration, and a set of actual virtual server farms or data centers can be created and deployed immediately. In one feature, the host's boot port is coupled to a directly attached storage network that includes a set of switching structures. In another feature, the placed storage is selected from one or more volumes of storage defined in a database. In another feature, the placed storage is selected from one or more connected volumes defined in the database. In addition, the storage utilization is determined in one or more sets of storage. 9 This paper size applies the Chinese National Standard (CNS) A4 specification (210X297 mm) (please read the precautions on the back before filling this page). Order the Ministry of Economy Printed by the Intellectual Property Bureau's Consumer Cooperatives 1231442 A7 ____B7 V. Description of the Invention (7) The set of storage units in the unit is now available and will be placed "immediately". In one approach, its disclosed configuration also facilitates the process of "immediately" changing the quality of service delivered with the storage. In particular, the quality of service can be identified to any given server using virtual targets. Disk arrays can be selected not only based on whether they are RAID disk arrays, but also on the quality of the underlying arrays. For example, a set of disk arrays may be a RAID disk array with a large number of caches; another disk array may be a plurality of disks that are not configured based on RAID and the like. Therefore, any SCSI port may be mapped to any disk array, with any desired quality, where π quality ’indicates the RAID status, the bandwidth to the memory, spindle size, manufacturer, etc. communication channel bandwidth. Other arguments include devices and computer-readable media that are configured to perform the above steps. Description of the Figures The present invention is shown by way of example rather than limitation. The figures in the drawings and their relative reference numbers refer to similar elements, and in which: Figure 1A is a block diagram showing a definition of a network computer Top of the system program-level graphics; Figure 1B is a block diagram showing the graphics of the processing program of Figure 1A in more detail; Figure 1C is a flowchart of the deployment of data center processing procedures based on this article; Figure 1D is a kind of Block diagram showing how it can be used to make a 10-sheet paper that is compliant with China National Standard (CNS) A4 (210X297 mm) ------ Ί ^ ι ·! (Please read the notes on the back before filling out This page) Order, Dance _ Printed by the Intellectual Property Bureau's Employee Consumption Cooperative of the Ministry of Economic Affairs 1231442 A7 B7 V. Invention Description (8) Customers and service providers in the configuration of the printed embodiment of the Employee Consumption Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs; Figure 2A is a block diagram of an example server farm, which is used to show the example of this article in which the embodiment can operate; Figure 2B is a diagram showing the phase of this diagram Flow chart of the steps; Figure 2C is a block diagram showing the processing procedure for automatically modifying the memory associated with the instantaneous data center; Figure 3A is a virtual memory layer for dynamically linking computer storage components with the processor A block diagram of one embodiment of the method; FIG. 3B is a block diagram of another embodiment of a method for dynamically connecting a computer storage element and a virtual memory layer of a processor; FIG. 3C is a diagram of dynamically connecting a computer Block diagram of another embodiment of the virtual memory layer method of storage elements and processors; Figure 4A is a block diagram of an embodiment of a storage area network; Figure 4B is a memory attached to the network Block diagram of the example of network production; Figure 4C is a block diagram of an example of production directly attached to the storage network; Figure 5A is a block diagram showing the interaction between the storage management client and the storage management server; Figure 5B Figure 6A is a block diagram showing the components of the control database; Figure 6A is a block diagram of the relevant components that generate the connection from the storage unit to the processor; Figure 6B is the storage that activates and links the virtual server farm Flow chart of the storage unit; 11 This paper size is applicable to Chinese National Standard (CNS) A4 specification (210X297 mm) (Please read the precautions on the back before filling this page): 4 · Order 1231442 Employees of Intellectual Property Bureau of the Ministry of Economy Cooperative printed A7 B7 V. Description of the invention (9) Figure 7 is a state diagram showing the state experienced by the disk unit during the above selection process; Figure 8 is a block diagram of a software component that can be used In the example production of a set of storage managers and related interfaces; and FIG. 9 is a block diagram of a computer system that can be used to make an embodiment. DESCRIPTION OF THE PREFERRED EMBODIMENT A method of a virtual memory layer for dynamically connecting a computer storage element to a processor is described. In the following description, numerous specific details are provided to provide a thorough understanding of the present invention. However, it will be apparent to those skilled in the art that the present invention can be easily understood without these specific details. In other instances, well-known structures and elements have been shown in block diagram form to avoid unnecessary confusion in the present invention. In this document, the names "pi virtual server farm", "VSF", "transient data center", and nIDC "are used interchangeably to indicate a network computer system that contains more than one A group of processors, one or more sets of storage elements, and one or more sets of protection elements or management elements, such as a combination of a firewall or a load balancer, and it passes through the large logical computing barrier of general computing elements and Aziz A request for a storage element of the specified type is created. These names explicitly exclude single workstations, personal computers, or similar computer systems containing a single box, one or more sets of processors, storage elements, and peripherals. The examples will be explained in accordance with the following organized document chapters: 1.0 Function View 12 This paper size applies the Chinese National Standard (CNS) A4 specification (210X 297 mm) ------------- -IT ------ Dance (Please read the notes on the back before filling this page) 1231442 A7 ____B7 V. Description of the invention (1〇) 1 · 1 Definition and examples of the transient data center 1.2 The area that constitutes the transient data center Block 2.0 illustrates disk storage based on instantaneous data center symbol definition. 2.1 Symbol definition method 2.2 illustrates disk storage based on symbol definition. 3.0 Virtual storage layer method for dynamically connecting computer storage components and processors. 3.1 The structure of the first embodiment 3.2 The structure of the second embodiment 3.3 The functions of the storage manager interaction 3.4 The database 3.4 The 3.5 software structure 3.6 The wide-area name space 4.0 The hardware 5.0 Extensions and Changes 1.0 Function Overview 1.1 Definitions and Examples Instantaneous Data Center Figure 1A is a block diagram showing the perspective of a method for defining a network computer system. The text representation of the logic configuration of the computer system is generated and stored, as shown in block 102. In block 104, one or more sets of commands of one or more sets of switching elements are generated according to the expressions herein. When the switching element executes the command, the network computer system uses logical ground to interconnect the computing elements. 13 This paper size applies to the Chinese National Standard (CNS) A4 specification (210X297 mm) I ^ " III (Please read the precautions on the back before (Fill in this page)

1T Dance Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 ___B7 V. Invention Description (11) Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs was created and motivated. In the preferred embodiment, the computing elements form a computing grid as disclosed by Aziz et al. Figure 1B is a block diagram showing more detailed graphics of the processing procedure of Figure 1A. Generally, the method of generating a data center representation includes a set of design phases, a set of production phases, a set of custom phases, and a set of deployment phases, such as the display of blocks 1 10, 1 1 2, 11 4, and Π 6, respectively. During the design phase, the logical description of the data center is generated and stored. Preferably, the logic description is generated and stored using software components that generate a graphical user interface, a graphical user interface that can be displayed by a standard browser computer program and receives its input. In this article, " browser " means a computer program that can display a webpage that complies with Hypertext Markup Language (HTML) or equivalent, and it supports Javascript and Dynamic HTML, such as Microsoft Internet Explorer, and so on. To generate a data center configuration, the user executes the graphical user interface tool. The user selects one or more sets of illustrations representing data center components (such as servers, firewalls, load balancers, etc.) from the available component palette. The end user drags one or more sets of illustrations from the palette to enter a set of workspaces, and connects these illustrations to the logical configuration required by the data center. In the production phase of box 1 12, the user can request and receive cost information from the service provider of the production data center. Cost information can include, for example, a set of set prices, monthly maintenance fees, and so on. Users can manipulate these illustrations into other configurations in response to cost information analysis. In this way, users can test a variety of configurations to an acceptable cost. 14 Paper sizes apply Chinese National Standard (CNS) A4 (210 X 297 mm) (Please read the notes on the back before filling out this page. )

1231442 A7 ____B7 V. Description of the Invention (12) Find someone who can provide enough computing power. (Please read the notes on the back before filling this page) In the custom phase block, after the data center is generated, a set of configuration programs are used to increase content information, such as web pages or database information, to use graphics One or more servers in the data center generated by the user interface tools. In the custom phase, users can save, copy, copy, and other edit and manipulate a set of data center designs. Further, the user can apply one or more sets of software images to a server in the data center. The selection of software images and their application to the server can be implemented depending on the role associated with the server. For example, if the first server appliance has the role of a web server, a set of HTTP server programs, a set of CGI program processors, web pages, and so on are given software images. If the server has a database server role, give a set of software images containing the database server program and basic data. As a result, users have complete control over the computers that form each data center component. Users are not restricted to using only predetermined locations or computers. In the deployment phase of block Π6, the data center generated by the user is explained in the calculation grid, activated, and the process is started according to the role of the server. Printed by the Employees' Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs Figure 1C is a flowchart of the process of deploying a data center based on the representations in this article. In block 1 40, the process obtains information from the actual device list to confirm one or more sets of components. The actual equipment list is a database list of components, connections, connection information, and status, and can be stored in, for example, the control plane database 135. In block 142, the processing program selects 15 paper sizes that are applicable to the Chinese National Standard (CNS) A4 specification (210X297 mm) 1231442 A 7 B7 V. Description of the invention (13) All records in the list identifying a group of idle specific component types . This type of record selection can, for example, be done using a star-like query statement using the SQL language available in the SQL database server. The database 131 also contains a VLAN table storing up to 4096 entries. Each item represents a group of VLANs. The limit of 4096 items reflects the information limit of Tier 2. In block 144, the handler chooses to use one or more sets of VLANs in the data center and maps the selected VLANs to the tags. For example, VLAN 値 π Π π is mapped to the tag 0uter_VLAN and VLAN 値 π12π is mapped to the tag Inner_VLAN. In block 146, the processing program sends one or more sets of messages to the hardware abstraction layer that forms part of the computing grid 132. Details of the hardware abstraction layer are as described by Aziz et al. This message indicates how the hardware abstraction layer places the CPUs of the computing gate 1 32 in a particular VLAN. For example, the message may contain information such as "component ID = 5", " port (or interface) = eth0 ", " vlan = vl ". A set of internal mappings are maintained, linking the port name (for example, "ethO" in this example) with the actual port and the number of leaves that are meaningful to a particular switch. In this example, assume that the mapping indicates that the port "ethOn" is璋 1, the blade 6 of the switching element 5. Further, the VLAN list stores a set of mappings, which indicate that "νΓ indicates the actual VL AN ,, 5". In response, the processing program can generate a message that configures port 1 and blade 6 to VLAN 5. The particular method of making block 146 is not essential. Importantly, the processing program sends information to the computing grid 132, which is sufficient to motivate the computing grid to select and logically interconnect one or more sets of computing elements and link storage elements to form a set of representations corresponding to a particular data center in this document. Data center. 16 This paper size applies to Chinese National Standard (CNS) A4 (210 X 297 mm) (Please read the notes on the back before filling out this page) Ordered by the Intellectual Property Bureau of the Ministry of Economic Affairs and printed by the Consumer Cooperatives 1234142 A7 B7 V. Invention Explanation (M) Figure 1D is a block diagram showing customers and service providers in a configuration that can be used to make an embodiment. The client 1 20 executes a browser 1 22, which can be any browser software that supports JavaScript as well as dynamic HTML, such as the Internet Explorer. The client 120 communicates with the service provider 126 via a network 124, which may be a local area network, a wide area network, one or more groups of the Internet, and so on. The service provider 126 is associated with a computing grid 132 having a plurality of processor elements and storage elements, as described by Aziz et al. With appropriate instructions, the service provider 126 can use the components of the computing grid 132 to generate and deploy one or more sets of data centers 134. The service provider also provides a graphical user interface editing server 128 and an administrative / management server 130 that interact with the browser 122 to provide data center definition, management, reconfiguration, and so on. The administration / management server 130 may contain one or more sets of autonomous processes each managing one or more sets of data centers. Such a handler is referred to herein as a farm manager. The customer 120 may be associated with an individual or business entity of a customer of the service provider 126. 1.2 Blocks for Establishing a Transient Data Center As detailed by Aziz et al., A data center can be defined using some basic building blocks. By selecting one or more sets of basic building blocks and specifying the interconnections between the building blocks, a data center for any required logical structure can be defined. The resulting logical structure can be named and processed as a blueprint (" DNA ") for any other IDC used to generate a set of identical logical structures. As a result, the creation of data centers has enabled many of the automated manual operations involved in building server farms using previous technologies. 17 This paper is sized to the Chinese National Standard (CNS) A4 (210X 297 mm) I " III (Please Please read the notes on the back before filling in this page.) Ordering · Printed by the Consumers 'Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 __B7 V. Description of Invention (15) Printing by the Consumers' Cooperatives of the Intellectual Property Bureau of the Ministry of Economy is more convenient. As defined here, the data center DNA can specify the role of the servers in the data center and the relationships between the various servers in the role. A set of roles can be defined once and then reused within a set of data center definitions. For example, the role of a web server can be defined using hardware, operating system, and related server applications, such as dual Pentium specifying minimum clock rate and memory size, NT version 4.0, with specified plug and play Component of Internet Information Server version 3.0. This web server role can then be replicated many times to generate a whole web server hierarchy. The role definition also specifies whether a role is used for machines that are statically assigned or dynamically added and removed from the data center. A basic data center building block is a load balancing function. This load balancing function can appear on more than a set of logical locations in the data center. In an embodiment, the load balancing function can be made using a hardware load balancing function of an L2-7 switching structure, which is obtained from Foundry Networks of San Jose, California. Inc.) is a commercially available Serverlron switch. A single hardware load-balancing component, such as the commercially available Serverlron product from Finder Networks, provides a number of logical load-balancing functions. Therefore, the specifications of a logical load balancing function generally include a set of virtual Internet Protocol (VIP) addresses and a set of load balancing strategies (for example, "minimum connection" or round-robin). A single component, such as Serverlron from Discoverer Networks, can support multiple VIPs (Virtual Internet Protocol) and different policies associated with each VIP. Therefore, a single finder network company 18 ϋ III--II-I (please read the notes on the back before filling this page) The paper size of this edition applies the Chinese National Standard (CNS) A4 specification (210X 297 mm) 1231442 A 7 B7 V. Description of the invention (16)

Serverlron elements can be used in a number of logical load balancing positions given to the IDC. An example of the use of a load balancing function is to specify a set of web server tiers to load balance using a specific load balancing function. For example, a two-tier IDC can have a set of network server hierarchies that have a database server hierarchy and have this type of load balancing. When the tier is linked to a load balancer, the automatic process changes the load balancer in response to the user adding / removing servers to / from the server tier. In other embodiments, other elements may be changed automatically. Another example use of a load balancing function is to specify a load balancing function for the application server hierarchy, which is logically located behind the load balancing network server hierarchy in a 3-tier configuration. This allows aggregation of application server hierarchies that use hardware load balancing to occur, rather than application specific load balancing mechanisms. This approach can be combined with application specific aggregation mechanisms. Other building blocks include firewalls, servers, storage, and so on. 2.0 Explanation of Disk Storage Based on the Symbol Definition of the Instantaneous Data Center In the archives on the 26th. In that description, a high-level symbolic validation language for use was revealed and used in other work to define disk storage associated with transient data centers. In particular, a disk definition is provided. Disk definition is part of the server role definition. A disk definition contains a set of drive names. 19 This paper size is applicable to the Chinese National Standard (CNS) A4 specification (210X297 mm) ------ J --- I — (Please read the precautions on the back before filling in this Page)-Ordered by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs, printed 1231442 A7 B7 V. Description of the invention (17) 値, drive size 値, and drive type 値. The drive name 値 is a set of mandatory, unique disk names. The drive size is not the disk size in megabytes. The drive type 値 is a mirror type of the disk. For example, a standard mirror pattern (specified using nStd " 値) can be specified. Additional drive types include " raid ", " performance ", " spindle ", " bandwidth ", or " other ", which may include tape drives, CD drives, etc. As a customary example, the text < disk drivename = " / test " drivesize = 200 drivetype = '’std " / > defines a 200Mb disk mapped on / test. One use of this definition is to designate a set of additional regional storage drives (for example, D: drives) as part of a Windows (W n d 0 w s) or Solaris machine. This is done using server-defined selected disk attributes. For example, the following component in the server definition specifies a regional drive name D: 200 servers with a capacity of 200MB. < disk drivename = MD * ", drivesize = M200 " < / disk > Although the drive name "D:" is given in the above definition, to show a specific example, such a name format is not required. Drive Name: You can specify a SCSI drive name or drive name in any other suitable format. In the Solaris / Linux environment, disk attributes can be used to specify, for example, a local file system with another file system, such as / home, as follows: < disk drivename = n / home ", drivesize = " 5 1 2 u > 20 This paper size applies Chinese National Standard (CNS) Α4 specification (210 × 297 mm) I: —I— (Please read the precautions on the back before filling this page)

1T 4 Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs Printed by 1231442 A7 B7 V. Invention Description (18) &lt; / disk &gt; In another method, &lt; disk〉 &lt; The / disk> tag indicates that a disk with the number of SCSI targets is used instead of the file system set point. For example, a disk definition may include the following syntax: &lt; disk target = M Ο &quot; drivetype = M scs i &quot; drivesize = M 8 6 3 1 M &gt; This indicates that, for the given server role, LUNs of size 8 63 1 MB should be mapped to SCSI drives at target 0 (and LUNO). Therefore, the disk label directly indicates information at the SCSI layer, rather than information at the file system layer. A full example field definition using a disk label is shown below. &lt;? xml version-51.05,? &gt; &lt; farm finlversion = ”1 · 1”> <tier id = ”37” name = `` Serverl ”&gt; &lt; interface name =” ethO ”subnet =” subnetl7 ” / &gt; &lt; role &gt; role 37 &lt; / role &gt; &lt; min- servers> l &lt; / min- servers &gt; <max- servers> 1 </ max- servers> &lt; init- servers> l &lt; / init -servers> &lt; / tier &gt; &lt; server-role id = &quot; role37M name = &quot; serverr, &gt; &lt; hw &gt; cpu-sun4u-x4 &lt; / hw &gt; &lt; disk target = M0M drivetype = MscsiM drivesize = &quot; 8631M &gt; 21 This paper size applies to Chinese National Standard (CNS) A4 (210X297mm) ------ Π 蝼 ----------- I # (Please read the Please fill in this page again) 1231442 A7 B7 V. Description of the invention (19) &lt; diskimage type = n systemn &gt; solaris &lt; / diskimage &gt; &lt; attribute name = M backup-policy &quot; value = Mnightly'7 &gt; &lt; / disk &gt; &lt; / server-role &gt;

<Subnet id = Msubnetl7M name = MIntemetMip = ,, extemalM mask = n255.255.255.240Mvlan = Mouter-vlan7 &gt; 2.2 Example of disk storage based on symbol definitions In one method, to create or implement this definition The farm manager places the correct disk space on the SAN-included components and uses the procedure described here to map the space to the correct machine. Most disk attributes can be used to specify another drive (or split from the point of view of the Unix operating environment). Disk components can also contain alternate strategies for specifying parameters such as RAID levels, one or more sets of selection attributes, and the use of attribute elements. Examples of attribute names and numbers are shown below. &lt; disk drivename = &quot; / homeM 5 drivesize = Μ512ΜΒΠ &gt; &lt; attribute name = nraid-level ”, valu =, '0 + l' '> &lt; attribute name =' 'backup-policy' ', value =' 'level = 0: nightly, &gt; &lt; attribute name = M backup-policy &quot; »value = &quot; level = l: hourlyM &gt; &lt; / disk &gt; / home specified above should be placed in RAID On level 0 + 1 drives, level 0 backups occur every night and level 1 backups occur every hour. Beyond time, other attributes can be defined for disk partitioning. 22 This paper standard applies Chinese national standards ( CNS) A4 specification (210X 297 mm) -------: --- II (Please read the notes on the back before filling out this page) Order 4 Printed by the Ministry of Economic Affairs Intellectual Property Bureau Staff Consumer Cooperatives Printed by the Ministry of Economic Affairs Printed by the Consumer Cooperative of the Property Bureau 1231442 A7 B7 V. Description of Invention (20) The embodiment can process the disk label defined here and automatically increase or decrease the storage quantity related to the data center or server farm. Section 2 A The figure is a block diagram of an example server farm. To demonstrate the example of this article that this embodiment can implement. Network 202 is communicatively coupled to firewall 204, which directs authorized traffic from the network to load balancer 206. One or more sets of CPU elements 20 8a, 20 8b 208c is coupled to the load balancer 206 and receives customer requests from the network 202 according to a designated or prioritized order determined by the load balancer. Each CPU in the data center or server farm is associated with storage. For Showing an obvious example, Figure 2A shows a storage element in a simplified form. The CPU 208a is coupled to a storage area network gateway 210 by a small computer system interface (SCSI) link, which provides the interface of a CPU with a SCSI port to The storage element or network using the optical fiber channel interface. In one embodiment, the gateway 210 is a Pathlight gateway and can be connected to 1-6 sets of CPUs. The gateway 210 has an output port using a fiber channel signal And is coupled to storage area network 212. One or more sets of disk arrays 214a, 2 14b are coupled to storage area network 2 1 2. For example, using an EMC disk array. Although Figure 2A shows only CPU 208a The connection to gateway 210 is that virtually all data center or server farm CPUs are coupled to the gateway by the SCSI connection, and the gateway thus manages all of the CPU's storage area network 2 1 2 and disk array 2 1 Designation of 4a, 2 1 4b. This configured system may have a memory and be automatically assigned and removed according to an automatic processing procedure that maps a part of the memory of the disk arrays 2 14a, 2 14b to one or more sets of CPUs. In the embodiment, the processing procedure and follow 23 paper standards are applicable to China National Standard (CNS) A4 specifications (210X297 mm) I ----- Η 丨 &quot; ------ IT ------: Qi (Please read the precautions on the back before filling out this page) 1231442 A7 B7 Printed by the Employees' Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs. 5. Description of the Invention (21) The storage data sheet of the track disk volume information is operated in combination. For example, in one embodiment of the table, each column is related to the logical unit of the memory and has rows that store the number of logical units, the size of the logical unit, whether the logical unit is free or used by the CPU , The logical unit where the disk array is placed, and so on. Figure 2B is a flowchart showing the steps involved in generating such a table. As indicated by block 221, these preliminary steps are generally performed before the processing procedure of Figure 2C. In block 223, information is received from a disk subsystem, the subsystem including one or more sets of logical units (LUNs) associated with one or more sets of volumes or connected volumes of storage in the disk subsystem. Block 223 may include receiving unit information from disk arrays 歹 ij 214a, 214b, or a controller associated with them. This information can be obtained by sending appropriate queries to the controller or array. In block 225, the volume information is stored in a list in the database. For example, an Oracle database can contain the appropriate list. The processing procedure of Figure 2B can be implemented when the transient data center is activated, or as a continuous operation in one or more groups of data centers. As a result, the FIG. 2C processing program may successively have sized images of the available memory in the memory subsystem of the CPU that is the server farm. Figure 2C is a block diagram showing a procedure for automatically modifying a memory associated with a transient data center. To show an example of analysis, the processing procedure of Figure 2C related to Figure 2A is illustrated, although the processing procedure can be used in any other suitable text. In the box 220, the item of data center that requires adding storage is described in item 24. The paper size applies to the Chinese National Standard (CNS) A4 specification (210X297 mm). 1 «Cloth ------ 1T ------ 0 ^ (Please read the notes on the back before filling this page) 1231442 A7 B7 V. Description of the invention (22) The <disk> label printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs was processed. Block 220 may include parsing files grammatically by specifying a data center or server farm using the validation language described herein, and identifying statements that require changes in the server farm's storage. In block 222, a database query is issued to obtain records sufficient to satisfy some of the additional storage requirements contained in the data center specification or disk tag storage. For example, where the disk label specifies a 30Mb disk storage, a set of SELECT queries are sent to the database table above to select and obtain a copy of all free volumes recorded up to 30Mb or more storage . When the generated results are received from the database, then in a format known to the disk subsystem, commands for some storage in the specified volume are generated, as shown in block 224. Where EMC disk storage is used, block 224 may contain a conversion volume command that specifies a specific number of storages that can meet the requirements in the disk label. In block 226, a request for adding disk subsystem storage is fulfilled using the commands generated in block 224. Therefore, block 226 may include transmitting a volume conversion command to disk arrays 214a, 214b. In block 228, the 'procedure receives information from the disk subsystem to identify and identify the number of memory locations placed and the number of locations using its logical units. In one embodiment, the connected volume may span more than one set of disk arrays or disk subsystems, and the number of logical units may represent storage units in a plurality of hardware units. In this context, "pi storage unit" refers to a logical unit (e.g., a LUN) within a single disk array, or a LUN of storage that encompasses a number of components that include disk drives, tape drives, Fast memory 25 ^ Paper size applies Chinese National Standard (CNS) Α4 specification (210X297 mm) ------ Ί-# -------, order ------- Qi (Please read first Note on the back, please fill out this page again) Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 B7 V. Invention Description (23) Access, CD, DVD, etc., or most logical or actual units or such Sub-units within the component. In block 230, the number of logical units received is provided to storage area network gateway 2 1 0. In response, storage area network gateway 2 1 0 generates one of its SCSI ports internally Maps to the number of logical units that have been received. As a result, gateway 2 10 can properly guide the information storage and retrieve requests that reach any of its SCSI ports to the correct disk array and logic within the disk subsystem Unit. Further, to specific The placement or designation of the CPU's memory is achieved automatically, and according to the text in the approved language file, the number of memory assigned to the CPU can be increased or decreased. 3.0 Dynamically linking computer storage components with the processor's virtual storage 3.1. Structure of the first embodiment. Figure 3A is a block diagram of an embodiment of a method of using a virtual storage layer to dynamically connect computer storage and a host. Generally, the virtual storage layer provides a Methods to dynamically and selectively connect storage, including boot disks and shared storage, to the host when the host is connected to and disconnected from the virtual server farm without adversely affecting host components such as the operating system and applications, and The host need not be involved. Most hosts 302A, 302B, 302N, etc. are communicatively coupled to the virtual storage layer 310. Each host 302A, 302B, 302N, etc. is a processing unit that is optionally designated To a virtual server farm as a processor, load balancer, firewall, or other computing element. Most storage units 3 04A, 304 B, 304N, etc. are communicatively coupled to the virtual storage 26. This paper size applies the Chinese National Standard (CNS) A4 specification (210X297 mm) &quot; I ^ 1 € clothing, order-0 ^ (Please read the note on the back first Please fill in this page for further information) Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 ___ ^ __ B7 V. Description of the Invention (24) Memory layer 310. Each storage unit 304A, 304B, 304N, etc. contains a group or more Multiple sets of disk subsystems or disk arrays. The storage unit may be used as the boot disk of the host 3 02 A, etc., or it can provide the host to share content at the block level or file level. The information stored in the storage unit associated with the host determines the processing role of the host. By changing the boot disk of the attached host, the role of the host may be changed. For example, a host may be associated with a first boot disk containing a Windows 2000 operating system over a period of time, and then such a relationship may be removed and the same host may be associated with a second boot disk containing a Linux operating system. As a result, the host becomes a LINUX server. The host can execute different software as part of the boot process to determine whether it is a web server, a specific application server, etc. Therefore, a host without another specific processing role can acquire a role by dynamically linking a storage component containing specific boot disk information or sharing content information. Each storage unit can be logically partitioned into one or more sets of logical units (LUNs) that can optionally be assigned to a virtual server farm. A LUN can contain a single disk volume or a connected volume containing multiple volumes. Therefore, any desired size storage can be placed from the storage unit by allocating any volume or scheduling the volume to the LUN, or instructing the storage unit to generate a connected volume containing a plurality of volumes, and then scheduling the storage volume. Connect the volume to the LUN. LUNs from different storage units can be assigned to a single virtual server farm in any combination to meet the storage needs of the virtual server farm. In one embodiment, the LUN can contain a single disk volume or span more than 27 paper sizes. Applicable to China National Standard (CNS) A4 specification (210X297 mm) ------ 14 ------, order- ---- 1 # (Please read the precautions on the back before filling this page) Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 B7 V. Description of the invention (25) In a set of storage units or disk arrays Connection volume. The virtual storage layer 3 10 establishes a dynamic link between the storage element and the host. In one embodiment, the virtual storage layer 3 1 0 includes one or more sets of storage gateways 30 06 and one or more sets of storage area networks 3 08. The virtual memory layer 310 is communicatively coupled to the control processor 312. Under the logical control of the executable program further explained here, the control processor 3 1 2 may instruct the storage gateway 306 and the storage area network 3 08 to connect to a specific group or groups of storage units 304. 1 ^ 1 ^ of 304, 304> 1, etc. and a specific virtual server farm, for example, to a specific host 302A, 3 02B, 3 02N. The control processor 312 may include a plurality of processors and supporting elements organized in a control plane. In this configuration, the virtual storage layer 310 provides storage virtualization from each host 302A and the like. Each such host can obtain storage via the virtual storage layer 310 without having to decide or know which set of specific storage units 3 04 A, 3 04B, 3 04N, etc. provide storage, and does not have to decide or know which set LUNs, blocks, volumes, other attached devices of the connected volume or storage unit actually contain data. Moreover, the LUN of the storage unit can be mapped to the boot port of a specific host so that the host can boot directly from the mapped LUN without modifying the application, operating system, or configuration data executed or controlled by the host. . In this article, &quot; mapping &quot; indicates the establishment of a set of logical designations or logical connections that lead to indirect actual routing, coupling, or connection between the host and the storage unit. The virtual storage layer 3 10 utilizes the protection of parts of a virtual server farm Storage is not subject to access from a host in another virtual server farm, and this paper size applies to Chinese National Standard (CNS) A4 specifications (210'〆297 mm) ^-丨 衣 丨 T # 7 ( (Please read the notes on the back before filling this page) 1231442 A7 B7 V. Description of the Invention (26) Increase security. The virtual storage layer 310 can be used as a virtual SCSI bus that provides mapping or connecting LUNs to the host. Here In this paper, the virtual storage layer 310 is exposed to the hosts 302A, 302B, and 302N as SCSI elements, and is itself addressed and accessed. Similarly, the virtual storage layer 310 is exposed as a SCSI initiator. Storage units 304A, 304B, 304N are given. Although the embodiment herein illustrates SCSI as a communication interface and protocol, any other suitable interface and protocol can also be used. For example, iSCSI can be Used, fiber channel communication can be through gateways, etc. Further, some embodiments described herein are LUN, volume, and connected volume or switch-volume. However, the present invention is not limited to this This article, and it can be any form of logic or actual mechanism that can be applied in the form of any number of conventional or later invented mass storage elements. Figure 3B is the use of a virtual memory layer to dynamically link computer storage and processors A block diagram of another embodiment of the method. One or more sets of control processors 320A, 320B, 320N, etc. are coupled to the local area network 3 30. For example, the LAN 330 may be an Ethernet circuit Control database 322, storage manager 324, and storage gateway 306A are also coupled to network 33 0. A storage area network (SAN) 3 08A is communicatively coupled to control database 322, storage manager 3 24, and storage gateway 306A, and to storage unit 304D. The control processor and control database can be organized with other supporting components in the control plane. In one embodiment , Each control processor 320A, 320B, 320N, etc. 29 This paper size applies to Chinese National Standard (CNS) A4 specification (210 × 297 mm) I ----- ^ τ € clothing II (Please read the precautions on the back first (Fill in this page again.) Order printed by the Intellectual Property Bureau of the Ministry of Economic Affairs, the Consumer Cooperatives printed 1231442 A7 B7 Printed by the Intellectual Property Bureau of the Ministry of Economics, the Consumer Cooperatives of the Ministry of Economic Affairs 5. Printed on the invention (27), etc., execute a storage manager customer 324C, which is related to the storage manager 324 communicates for storage manager functions. Further, each control processor 320 A, 3 20B, 3 20N, etc. executes a field manager 326, which executes a virtual server field management function. In a particular embodiment, the storage manager client 324C provides an API to the field manager 326 which can call the functions of the storage manager 324 to perform the storage manager function. Therefore, the storage manager 324 is responsible for performing most of the basic storage management functions, such as copying a disk image from a storage unit, etc., and deleting information ('' except net π). Further, the storage manager 324 directly interacts with the storage unit 304D to perform storage unit-specific functions, such as providing designated gateway access to the LUN, generating connected logic, linking the LUN to the volume or the connected volume, etc. Wait. Certain combined operations on the memory gateway 306A are implemented using a function defined in the API of the call field manager 3% to the memory gateway 306A. In particular, the storage gateway 3 06A is responsible for connecting the host to the optical fiber channel and switching the structure to connect the host to the storage element. In the configuration of Figure 3A or Figure 3B, the control processors 320A, 3 2DB, 3 20N may also be coupled to one or more sets of switching elements, which are then coupled to form a virtual server from there Farm host. Further, one or more sets of power controllers may participate in the virtual storage layer 3 1 0 or may be coupled to the network 3 3 0 to selectively power and power off the host 30 02. Figure 4A is a block diagram of one embodiment of a storage area network 308A. In this embodiment, the storage area network 3 08 A is made into two sets of networks, which respectively provide network attached storage (NAS) and direct attached storage 30 ------ ^ --- Γ Clothing-(Please read the precautions on the back before filling this page),? Τ This paper size applies to the Chinese national standard (CNS> Α4 size (210 × 297 mm) 1231442 A7 B7 Printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs Description of the invention (28) (DAS). One or more sets of control database 322 A, 322B are coupled to the control network 4 01. One or more sets of storage managers 324A, 324B are also coupled to the control network. Road 40 1. The control network is further communicatively coupled to one or more sets of disk arrays 404A, 404B, which participate in the network attached storage network 408 and the direct attached storage network 402, respectively. In the example, the network-attached storage network 408 includes a plurality of data moving servers that can receive network requests for information stored in the storage unit 404B and respond to the requested data. Disk Array Controller 4 0 6B communication ground is coupled to disk array 404B To control the data transfer between them and the NAS network 408. In a particular embodiment, the EMC Celerra data mover associated with the disk storage found within the disk array is used. Most storage Device gateways 306A, 306B, 306N, etc., participate in the direct attached storage network 402. Most disk arrays 404A are coupled to the DAS network 402. The DAS network 402 contains a plurality of switching elements. Each disk array 404A Is coupled to at least one set of switching elements, and each memory gateway is coupled to a set of switching elements. One or more sets of disk array controllers 406A are communicatively coupled to disk array 404A to control them And data transfer in the D AS network 402. The control processor operates the volume information in the disk array and issues commands to the storage gateway to cause the combination of one or more disk volumes to be provided to the virtual server farm. Host used in. A commercially available symmetric disk array from EMC (Hopkinton, Massachusetts, USA), or similar, can be used as a disk 31 as appropriate ------: --- Clothing-(Please read first Please fill in this page again if you need to pay attention to the above) The size of the paper is applicable to the Chinese National Standard (CNS) A4 (210X297 mm) 1231442 A7 A7 B7 V. Description of the invention (29) ------ ^ --- 7 · ^^ Clothing-(Please read the precautions on the back before filling out this page) Array 404B. The combination of EMC storage and Celerra data mover connected to the disk storage found in the disk array can be used in Disk array 404A. Commercial memory gateways, or similar components, from Pathlight Technology, Inc./ADIC (Redmond, Washington) are suitable for use as memory gateways 306A and the like. Commercial switches from McDATA Corporation (Broomfield, Colorado) are suitable for use as switching components of the DAS network 402. The Intellectual Property Bureau of the Ministry of Economic Affairs ’s Consumer Cooperative ’s printed storage gateway provides a set of devices to couple processor storage ports, including but not limited to SCSI ports, to a storage element, including but not limited to participating in storage of fiber channel networks element. In this configuration, the storage gateway also provides a way to prevent WWN (Worldwide Name) from "spoofing". An unauthorized server mimics the address of an authorized server to gain access to restricted data. . The gateway is communicatively coupled to a plurality of disk arrays, and virtual access to a large amount of data is induced through a group of gateway elements. Further, in the SCSI article, the storage gateway creates a separate SCSI name space for each host, so that the host operating system does not need to change to map a set of disk volumes to the host's SCSI port. In addition, the storage gateway facilitates opening the operating system from the central storage without modifying the operating system. The control network 401 includes a storage area network which has access to all the disk array volumes. In one embodiment, the control network 401 is configured on two ports of all the disk arrays 404A, 404B. Control network 40 1 is used to copy data in or between disk arrays; operating disk array capacity 32 This paper size applies Chinese National Standard (CNS) A4 specifications (210X297 mm) 1231442 A7B7 Intellectual property of the Ministry of Economic Affairs Printed by the Bureau ’s Consumer Cooperatives. V. Invention Description (30), remove data from disks, and provide storage for control database. The above configuration also facilitates the process of changing the quality of service delivered by the storage "on the fly". In particular, the quality of service can be distinguished from any given server using virtual targets. For example, SCSIO may be RAID 1, however SCSI1 may be RAID5, SCS12 may be a tape drive, etc. Disk arrays can be selected not only based on RAID, but also based on the quality of the array placed below. For example, a group of disk arrays can have a A large cache of Symmetrix disk arrays; another disk array can be multiple disks that are not configured based on RAID ("just a string of disks" or a group of "JBOD" arrays), etc. Therefore, any SCSI port may be mapped to any disk array of any desired quality, where "Quality" indicates the RAID status, the bandwidth of the communication channel to the storage, the spindle size, the manufacturer, and so on. Figure 4B is a block diagram of an example of a network-attached storage network 408. In this embodiment, the network attached storage network 408 includes a plurality of data moving servers 410, which can receive network requests for information stored in the storage unit 404B and reflect the requested data. In one embodiment, there are 42 data moving servers 410. Each data moving server 4 1 0 is communicatively coupled to at least one of a plurality of switches 412A, 412B, 412N, and so on. In a particular embodiment, the switches are Brocade switches. Each switch 412A, 4 12B, 4 12N, etc. has one or more groups of ports coupled to one of the plurality of disk arrays 404B. The pair of disk arrays 404B is coupled to control data transfer between them and N such as network 408 33 I ------: --- 7 &quot; ^ 衣-(Please read the Note: Please fill in this page again.) The size of the paper is applicable to the Chinese National Standard (CNS) A4 (210X297 mm) 1231442 A7 B7. Printed by the Intellectual Property Bureau of the Ministry of Economic Affairs, Consumer Cooperatives.器 406B. Figure 4C is a block diagram of an example of a direct attached storage network 402. In this embodiment, at least one group of servers or other hosts 303 are communicatively coupled to the plurality of gateways 306D, 306E, and so on. Each gateway is coupled to one or more sets of data switches 4 1 4A, 4 1 4B. Each switch is communicatively coupled to a plurality of storage elements 404C using a link 416. In a particular embodiment, the switch is a McDATA switch. Each switch 4 1 4 A, 4 1 4B, etc. has one or more ports coupled to one of the plurality of disk arrays 404C. Port group identification identifies various switching configurations including switches and disk arrays. For example, in a particular embodiment, the first structure is defined by switches labeled "quasi-bi 3A" and "14BΠ" coupled to disk array 404C; the second structure is coupled to "4A", "15B" Switch · defined, etc. 3.2 Structural overview of the second embodiment Fig. 3C is a block diagram of the virtual memory layer method according to the second embodiment. The plurality of hosts 302D are communicatively coupled to the virtual storage element 340 using respective SCSI channels 3 3 0D. The virtual storage element 340 has a RAM cache 344 and is coupled to one or more sets of disk arrays 304C using one or more sets of Fibre Channel storage area networks 346. The link 348 from the virtual storage element 340 to the optical fiber channel SAN3 46 and the disk array 304C is a fiber channel link. The virtual storage element 340 is communicatively coupled to the control processor 3 1 2 which performs steps to map the given logical disk to the host. Logical Disk 34 ------ ^ ----- (Please read the notes on the back before filling this page)

， 1T This paper size applies the Chinese National Standard (CNS) A4 specification (210 × 297 mm) 1231442 A7 B7 V. Description of the invention (32) Printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Economics, it can be printed for shared access, or for unique storage. Instead, it is mapped. An example of a unique access configuration is when the logical disk behaves like a set of boot disks that contains the only complete server configuration information. In this configuration, the virtual storage element 340 plays a role in the SCSI target mode, such as using an indication of a SCSI target connection 342D that provides a SCSI disk interface to a host functioning in a SCSI boot mode via a SCSI link 33 0D. The virtual storage element 340 can interact with many hosts and provide virtual disk services to them. The virtual storage element 340 may perform a function that provides improved storage efficiency and performance efficiency. For example, by performing the address conversion of the number of SC SI units and the number of blocks in real time, the virtual storage element 340 can subdivide a set of a single large RAID disk array into many logical disks. As a specific set of examples, most hosts may require SCSI unit 0, block 0. These requirements can be mapped to a single set of disk arrays by using the number of translation blocks as offsets within the disk array. Utilizing a secure logical partition that provides many disk arrays, this allows many customers to use a single set of disk arrays together. Further, the virtual storage element 340 can use its RAM cache 344 to cache disk data. In particular, by using the cache function under the control of the control processor 3 1 2 and under the strategy established by the control processor, the virtual storage element can provide the RAM cache of the page block of the operating system, thus increasing the availability for specific hosts. Fast amount of virtual memory. 3.3 Function Overview of Storage Manager Interaction Figure 5A is a block diagram showing the interaction between the storage manager client and the storage manager server. 35 This paper size applies Chinese National Standard (CNS) A4 specification (210 X 297 mm) I ----- ^ ----- (Please read the precautions on the back before filling this page) -5 · 口 1231442 Printed by the Consumer Property Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs A7 B7 V. Invention Description (33) In this exemplary embodiment, the control processor 320A includes a computing service element 502, a storage manager client 324C, and a gateway hardware abstraction layer 504 . The computing service element 502 is a subsystem of the field manager 326. The field manager 326 is responsible for calling a storage function for determining the placement of a disk, a VLAN, or the like. The storage manager client 324C is communicatively coupled to the storage manager server 324 in the storage manager server machine 3 24A. The gateway hardware abstraction layer 504 is communicatively coupled to the memory gateway 3 06 A and provides a set of software interfaces so that external program components can call interface functions to access the hardware functions of the gateway 3 06 A. The storage manager server machine 324A additionally includes a disk array control center 506, which is communicatively coupled to the disk array 304D, and a component driver 508. The request for the storage management service is connected from the storage manager client 3 24C to the storage manager 3 24 via the network link 510. The details of the above elements are also explained here in conjunction with FIG. 8. In this configuration, an application program interface is made to the storage manager client 3 24C. The storage manager server 324 can call one or more of the following functions:

Discovery

Bind

Scrub

Copy

Snap

Meta Create

Discovery command, when the manager customer stored by the controlled processor 36 This paper size applies to Chinese National Standard (CNS) Α4 specification (210X297 mm) I ^ IT (Please read the precautions on the back before filling this page) 1231442 A7 B7 5. Description of the invention (34) 3 When 24C is sent to the storage manager server 324, it instructs the storage management server to find all available storages on the network. In response, the storage manager sends one or more sets of requests to all known storage arrays to identify all available logical unit numbers (LUNs). Based on the information received from the storage array, the storage manager server 324 generates and stores information representing the storage in the system. In one embodiment, the storage information is organized in one or more sets of disk wiring mapping language files. Here a set of disk wiring mapping languages is defined as a structural validation language representing disk components. The information in the wiring map language file represents disk attributes, such as disk identifier, size, port, SAN connection, and so on. Such information is stored in the control database 322 and used as a benchmark for LUN placement and bonding operations. The remaining API functions are illustrated in Figure 6A, which is a block diagram of the components that generate the combination of the storage unit and the processor. In the example of FIG. 6A, the control database 322 is accessed using the control center or gateway 602, the clip manager 604, the field manager 606, and the storage manager 324. A control center or gateway 602 is one or more sets of applications that motivate a set of individuals to define, deploy, and manage account information about one or more sets of virtual server farms. For example, using the control center 602, a user can ask a graphics editor to visually define a virtual server farm using graphical illustrations and connections. The symbol of the virtual server field indicates that it is then generated and stored. Symbolic representations can contain files in a certified language, where disk storage is specified using one or more sets of "disk" tags and "component π" tags. Other functions of Control Center 602 are on the 37-paper scale Shiyuan China National Standard (CNS) Α4 Specification (210X297 mm) One ------ 1 --- 1-(Please read the precautions on the back before filling this page)

1T Printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 B7 V. Description of Invention (35)

Patterson et al.'S pending US application serial number 09 / 863,945, described in a file filed May 25, 2001. The fragment manager 604 manages a plurality of processors and a storage manager, and includes a set of computing grid fragment processing structures and cooperates to generate, maintain, and not activate one or more sets of virtual server farms. For example, there may be many processors or hosts in the computing grid segment. The argument of the fragment manager 604 is illustrated in the pending application serial number 09 / 630,440 of Aziz et al., Filed on September 30, 2000. The field manager 606 manages the description, maintenance, and deactivation of specific virtual server fields. For example, the field manager 606 receives the symbol description of the virtual server field from the control center 602, analyzes and interprets the symbol description, and arranges, logically and physically connects one or more groups of processors required to make the virtual server field. . Further, after a specific virtual server farm is generated and deployed, additional processors or storage connections are brought to the virtual storage farm or removed from the virtual storage farm under the control of the field manager 606 . The storage manager 324 is communicatively coupled to the control network 4 (H, and the control network 401 is communicatively coupled to one or more sets of disk arrays 404A. Most operating system images 6 1 0 are connected to the disk array The methods are stored. Each operating system image contains a pre-defined combination of a set of executable operating systems, configuration data, and one or more sets of applications that perform the required functions, which are packaged as loadable to Images of storage components. For example, there are a set of general windows 2 0 0 images, a set of images containing Sun οft S ο 1 ar is, an Apache web server, and one or more networks Application, etc. Therefore, a set of operating system images from 6 1 to 60 are used to be combined into 38. This paper size applies the Chinese National Standard (CNS) A4 specification (210X297 mm) ------- ^ --- 1 -(Please read the notes on the back before filling this page)

1.1T printed by the Consumer Cooperative of Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 _____B7 V. Invention Description (36) (Please read the precautions on the back before filling this page) The storage unit where the processor is placed, and the virtual server farm is obtained. Specify the operating software and application software required for the function. Fig. 6B is a flowchart of a processing procedure for initiating and combining a virtual server field storage unit in an embodiment. At block 620, the storage requirements are communicated. For example, when a new virtual server farm is generated, the control center 602 communicates the storage requirements of the new virtual server farm to the segment manager 604. In block 622, a request for storage placement is issued. In one embodiment, the fragment manager 604 quickly processes the storage placement request to the field manager 606. Sufficient resources are then placed, as indicated by block 624. For example, the field manager 606 queries the control database 322 to determine which storage resources are available and to place sufficient resources from the disk array 404A. In one embodiment, the LUN contains 9GB of storage with zero boot on the SCSI port. Alternatively, the host may power on at any target (which is typically 0 to 25 5 targets) addressed via its SCSI port. Another number of variable-size memories are available for specifying one to six SCSI ports. Printed by the Consumer Property Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs. Such placement may include placement of disk volume, LUNs, or other disk storage blocks that are discontinuous and are not logically organized as a single disk portion. Therefore, a processing program that joins these discontinuous disk blocks is needed. Thus, at block 626, a method for allocating a memory-to-memory conversion element is generated. In one embodiment, the field manager 606 requests the storage manager 324 to generate a transform-element containing all the disk blocks that have been placed. Storage Manager 324, a group of 39 known through the disk array. This paper size applies the Chinese National Standard (CNS) A4 specification (210X297 mm) A7 B7 1231442 i 'Invention (37) or more sets of commands, using magnetic The disk array 404 A sends a message to generate the required conversion-component. In another method, the placed storage is selected from a database 'such as a control database, one or more sets of volumes of defined storage. In another feature, the placed storage is selected from one or more connected volumes defined in the database. Alternatively, 'utilize' that storage and then place the storage in one or more sets of storage units that are currently available &quot; on the fly '. The definition of the volume or connected volume in the database can be implemented in advance using the manager. In another method 'all available reservoirs are represented using storage tanks and appropriately sized volumes are placed as needed. When the conversion-element is successfully generated, the storage manager 324 notifies the field manager 606 and provides information identifying the conversion element. In response, the master image that can execute the software instructions is copied to the conversion-component, as indicated by block 628. For example, the field manager 606 requests the storage manager 324 to copy the selected main image from the operating system image 6 10 to the conversion element. The storage manager 324 issues an appropriate command to cause the disk array 404A to copy the selected master image from the operating system image 610 to the conversion-element. The conversion-element is incorporated into the host, as shown in block 630. For example, the 'field manager 606 then asks the storage manager 324 to combine the conversion-elements to the hosts participating in the virtual server farm. Such a processor is shown in the host 608 of FIG. 6A. The storage manager 3 24 issues one or more sets of commands that cause the appropriate combination to occur. In one embodiment, the combined processing program has two sub-steps, shown by blocks 630A and 630B. In the first sub-step (block 630A), the field manager 606 calls the function of the storage manager client 324C, the storage tube 40 paper size applies to the Chinese National Standard (CNS) A4 specification (210X297 mm) (please read the back first) (Please note this page and fill in this page again), printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs, printed by 1231442 A7 B7 V. Description of the invention (38) The processor client 324C instructs a specified group of LUNs to be combined into a specific port of the specified host A bank of storage gates 306A. For example, the storage manager client 324C may instruct a set of storage gateways 3 06A that the LUN "17" is coupled to the SCSI port 0 of a particular host. In a specific embodiment, the LUN is always bound to SCSI port 0 because the port is defined in the host's operating system as the boot port of the operating system. Therefore, after combining the LUN "17" to the SCSI port 0 of the host A, the storage manager client 324C can issue a command to combine the LUN "18" to the SCSI port 0 of the host B. Through this combination, the host can boot from storage elements located far away in the central disk array, and still consider the storage elements to be near the area of SCSI port 0. In the second sub-step (block 63 0B), the field manager 606 uses the storage manager client 324C to instruct the disk array 404A to give the storage gateway 3 06 A access to be combined into the first sub-step One or more sets of LUNs for the host port. For example, if host A and host B are both communicatively coupled to storage gateway 306A, storage manager client 324C instructs disk array 404A to give storage gateway 306A access to LUN &quot; 17 &quot; and LUN ', 8,,. In a specific embodiment, when the connected volume of the disk array 404A is combined to the port containing the host 608 via the DAS network 402, a set of Bind-Rescan commands are used to cause the storage gate Channel 306A is obtained to the combined volume of the connected reservoir. The field manager 606 separately uses one or more sets of Bind-VolumeLogix commands to connect or combine a specified set of disk-connected volumes with specific ports that are switched in the DAS network 402. The specific sub-steps of blocks 630A and 630B shown here provide 41 papers that are again applicable to the Chinese National Standard (CNS) A4 specifications (210 × 297 mm) ------: --- clothing-(Please read first Note on the back, please fill out this page again), 1T printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 Α7 Β7 printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 5. Specific examples of inventions (39). However, the embodiment is not limited to such sub-steps. Any mechanism for automatically and selectively combining a designated storage unit to a host computer may be used. Any further configuration required is then implemented, as indicated by block 63 2. For example, the farm manager 606 then completes any further configuration operations required for any aspect of the virtual server farm related to other constructs. Other configurations of this type can include: triggering a power controller to apply power to a virtual server farm, scheduling hosts to a load balancer, and so on. The host then boots from the conversion-element, as indicated by block 634. For example, the host 608 is powered using a power controller and is powered on from its original boot port. In one embodiment, the standard boot port is SCSI port 0. As a result, the host boots from the operating system image of the combined connected volume that has been copied to the storage. Referring again to FIG. 5A, the component driver 508 is a SCSI component driver that provides direct access to the disk components with a low level to the software components described above. In general, the component driver 508 facilitates image reproduction from a large volume to a large volume. MORE Computer Services has provided the appropriate component drivers with information at ‘somemore’ dot com Web location. In a particular embodiment, the MORE component driver is modified to allow a plurality of open operations on the component, thereby facilitating one-to-many copy operations. The component driver is further modified to provide end-of-media detection for simple manipulations such as large-to-large copies. Fig. 7 is a state diagram showing the states experienced by the disk unit in the above-selected program. In this article, the name "disk unit" is broadly defined. 42 paper sizes are applicable to the Chinese National Standard (CNS) A4 specification (210X297 mm). I ----- ^ --- clothing-(Please read the Note for this page, please fill in this page)-, 1T 1231442 A7 B7 V. Description of the invention (40) I ----: ----- (Please read the notes on the back before filling this page) to indicate that a group is connected Disk block volume or disk array. In one embodiment, the control database 3U stores a state identifier corresponding to the state identification of each disk unit in FIG. 7A. Initially, a group of disk units was in free State 702. When the field manager controlling the processor places a set of volumes containing the disk unit, the 'disk unit enters the placed state 704. When the field manager generates a connected volume containing the placed disk unit, As instructed by Make Meta VolUme 708, the disk unit enters the configured state 710. The manufacturing conversion volume transfer 708 represents an alternative method 'wherein the connected storage volume is "immediately" followed by Produced in currently available storage Raw. In another method, the placed storage is selected from a database, such as a control database, and one or more sets of storage volumes are defined. In another feature, the placed storage is selected from one or more groups of connected volumes defined in the database. The definition of the volume or connected volume in the database can be implemented using a set of previous managers. In another method, all available reservoirs are represented by storage tanks and appropriately sized volumes are placed as needed. Printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs. If the manufacturing transfer volume transfer 708 fails, if combined with the failure transfer 7 1 1 instruction, the disk unit enters an unconfigured state 7 1 4. When the field manager sends a request to copy the disk image to the configured volume, as indicated by the transfer 709, the disk unit remains in the configured state 7 1 0. If the disk image copy operation fails, then the disk unit uses the transfer 7 1 1 to enter the unconfigured state 7 1 4. When the combination transfer 7 1 5 is performed, the magnetic disk unit enters the combined state. 43 This paper size applies the Chinese National Standard (CNS) A4 specification (210 X297 mm) 1231442 A7 B7 V. Description of the invention (41) 7 1 6 ° But 'If the combined operation fails, as indicated by combined failover 7 丨 2', the disk unit enters an unconfigured state 7 1 4. From the combined state 7 1 6, the disk unit is generally mapped to the processor by the storage gateway, as indicated by the mapping transfer 7 1 7, and enters the mapped state 724. If the mapping operation fails, as indicated by the mapping failover 7 1 8, any existing bond is removed and the disk unit is moved to the unbonded state 720. The disk unit can then return to the coupled state 7 1 6 via the disk array combination transfer 72 1, which is the same as the bulk processing up to the combination transfer 7 1 5. When in the mapped state 724, the disk unit is used in a virtual storage farm. The fe disc unit may undergo a point-in-time copy operation, a division or concatenation operation, and the like, such as an instruction of division / combination transfer 726. When such an operation is completed, the disk unit remains in the mapped state 724. When the virtual server farm is terminated or the storage unit is no longer needed, it is not mapped from the virtual server farm or its processor, as indicated by the unmapped transfer 727, and enters an unmapped state 728 . The bond to the processor is removed, as indicated by unbound transfer 729, and the disk unit enters an unbound state 720. After the disk unit remains in the unlinked state 720, the data on the disk unit is then removed or deleted, as indicated by the delete transfer 730 instruction. When the field manager issues a command to suspend the connected volume containing the disk unit, as instructed to abort the transfer-volume transfer 7 3 1, the disk unit enters an unconfigured state 7 1 4. The field manager may then not place the volume, as indicated by the transfer 732, which causes the disk unit to return to a free state 702 so that 44 paper sizes are applicable to the Chinese National Standard (CNS) A4 specification (210X297 mm) ----- -^ --- II (Please read the notes on the back before filling out this page) Order printed by the Intellectual Property Bureau Employee Consumer Cooperative of the Ministry of Economic Affairs 1231442 A7 B7 V. Description of the invention (42) Reuse sequentially. Therefore, automatic procedures for allocating and combining storage to virtual server farms have been described. In an embodiment, the disclosed processing procedure provides direct storage to a virtual server farm in the form of an scsim indicator. The storage can be backed up and can accept destructive or non-destructive re-storage operations. Any Fibre Channel element can be mapped into the processor SCSI address space. Memory security is provided as if centrally managed. Direct-attached storage and network-attached storage are supported. The process is independent of any operating system device and does not conflict with any required operating system or application configuration or disk image. In particular, although the basic hardware is reconfigured to cause the memory unit or volume to be mapped to the host, applications and operating systems running on the host do not perceive that the host has been bound to a particular data storage unit. Therefore, a transparent storage resource configuration is provided. 3.4 Database Schema In a particular embodiment, the disk wiring map identifies one or more sets of components. For example, the component is a disk array. For each component, one or more sets of attribute names and data are presented in the archive. Examples of attributes include component name, component mode, number of component strings, and so on. The disk wiring map also identifies the names and identifiers of the ports on the control network 401. Also in a specific embodiment, the definition of each element includes one or more sets of volume definitions related to the element. Each disk volume definition includes the identifier or name, size, and type. Disk volume attributes for one or more pairs and their numbers can be provided. Example of Disk Volume Attributes 45 This paper size applies to Chinese National Standard (CNS) Α4 size (210 × 297 mm) ιϋ · ^^ 1 * ^ 1 | I----ϋ ml m I (Please read the note on the back first (Please fill in this page)

Printed by 1T Consumer Cooperatives, Intellectual Property Bureau, Ministry of Economic Affairs, 1T

Fifth invention description (43) Contains status, configuration type, spindle identifier, and so on. Disk volume definition also identifies the volume ports on the control network and the number of logical units in the disk volume. Figure 5B is a block diagram showing the components of the control database. In one embodiment, the control database 322 includes a disk table 5 1 0, an optical port table 5 1 2, a disk optical port table 5 1 4, and a disk combination table 5 16 Disk table 5 10 contains information about the individual disk volumes in the disk array. Disk arrays are represented as a set of actual components. In a particular embodiment, the disk table 5 10 contains the information shown in Table 1. Table 1 _Disk Table I ----, ----- (Please read the notes on the back before filling out this page)

Row Name Type Description Disk ID Integer Disk Serial Number Disk Array Integer Disk Array Component Identifier Disk Volume ID Serial Disk Volume Identifier Disk Type Serial Disk Volume Type Disk Size Integer MB Volume Disk Size Disk body integer body disk ID. If the associated disk is a part of the connected disk group that constitutes a larger volume, the disk sequence integer is set to the serial position disk in the connected disk. BCV integer disk. The spare control volume ID Disk field ro sequence This disk is currently assigned the field ro Disk time stamp date The last modification time mark currently recorded The disk status sequence is the disk status in the state shown in Figure 7 (e.g. , Unoccupied, placed, etc.) Disk image ID Integer software image ID of any image on the disk Optical fiber attached port table 512 describes the optical fiber attached (FA) port information of each disk array. In a specific embodiment, the table 5 1 2 attached to the optical fiber contains 46 of Table 2. This paper size is applicable to the Chinese National Standard (CNS) A4 specification (210 × 297 mm) 1231442 A7 B7 V. Description of the invention (44) information. Table 2 _ Disk table line name type description FAPID Integer fiber with port identifier; internally assigned unique integer FAP disk array integer to the storage array identifier FA port ID sequence element FAP identifier specific component global global name sequence The worldwide name of the fiber attached port FAP SAN serial to the attached FAP storage area network name FAP type serial FAP type, for example, back-end or front-end FAP reference count integer FAP reference count; identify the use of this port to connect to the disk volume CPU number. I ---- ^ --- clothing-- (Please read the precautions on the back before filling in this page) Disk table with port table 514 describes the FA port to LUN mapping for each disk, and can include the table 3 Recognized information. Table 3- Disk and fiber attached table and row name Type Description Disk ID Integer disk volume identifier; Indicate disk table 510 Item FAP identifier Integer fiber with port identifier; Instruct fiber with port table 512 Item LUN sequence This The name of the logical unit of the disk on the port of the optical fiber. In one embodiment, the disk combination table 5 16 is a dynamic table describing the relationship between the disk and the host with access to the disk. In a specific embodiment, the disk combination table 5 16 has the information identified in table 4. 47 This paper size applies the Chinese National Standard (CNS) A4 specification (210 × 297 mm), printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 B7 V. Description of the invention (45) Table 4-Magnetic disk combination table row Name Type Description Disk ID Integer disk volume identifier; indicates the item of disk table 510. Port ID Integer FAP identifier; indicates entry S of the port table attached to the fiber where the disk will be accessed. Host ID Integer CPU component identifier indicator for access disk Integer CPU SCSI target identifier for access disk LUN Integer CPU SCSI LUN identifier for access disk Printed by the Intellectual Property Bureau of the Ministry of Economic Affairs Employee Cooperative Organization 3.5 Software Structure Figure 8 is a block diagram of software components that can be used to make examples of the memory manager and related interfaces. The field manager wiring category 802, which forms part of the field manager 3 26, is the main customer of the storage service represented by the other elements of Figure 8. The farm manager wiring category 802 may call a function of the SAN fabric interface 804, which defines the associated storage services available and provides an application planning interface. The functions of the SAN fabric interface 804 are fabricated in a SAN fabric production 806, which is tightly coupled to the interface 804. The SAN fabricator is a function that is communicatively coupled to the SAN gateway interface 808 and can call the SAN gateway interface 808, which defines the services available from the storage gateway 306. Such a service is produced in SAN Gateway Fabrication 80, which is tightly coupled to the SAN Gateway Interface 808. The storage manager service layer 812 defines the services made by the storage manager, and its functions can be stored in the storage manager server machine 3 24A 48 ------ ^ ---- 1STII (Please read the note on the back first Please fill in this page again for the paper) The size of the paper is applicable to Chinese National Standard (CNS) A4 specification (210X297 mm) 1231442 A7 B7 Printed by the Intellectual Property Bureau of the Ministry of Economic Affairs Employee Consumer Cooperatives V. Invention Description (46) Register Manager Customer 324C And storage manager server 324. In a specific set of embodiments, the client storage management service of the storage manager client 324C is made using the storage manager connection 814. The storage manager connection section 814 transmits a service request to the request queue 8 1 6. The storage manager connection 8 1 4 is communicatively coupled to the storage manager request processor 8 1 8, which requests to leave the queue from the storage manager connection and forward the request to the request processor 820. The processor 820 is required to accept the requirements of the memory service and execute them. In a particular embodiment, for the required storage, the request queue 8 16 is made using a highly available database. Queue items are defined to contain Java® objects and other complex data structures. In one embodiment, the request processor 820 is a communication type with a service routine that is made as a stand-alone Java® or Perl program, as indicated by the memory integration layer program 822. For example, the memory integration layer program 822 provides component access control, a set of point-in-time copy functions, conversion component management, and other management functions. In a specific embodiment, where the storage arrays are EMC products, access control is provided by EMC's VolumeLogix program; point-to-time copy functions are provided by TinieFinder; conversion element component management is configured by EMC Symmetrix Manager (&quot; symconfig "); and other management provided by EMC Control Center. Storage manager type 824 is responsible for startup, configuration, and other functions. SAN gate production 8 1 0 keep The structure of the data in the memory is 49 I --------- (Please read the precautions on the back before filling this page) The size of the paper is applicable to the Chinese National Standard (CNS) Α4 specification (210X 297) 1231442 A7 B7 Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs V. Invention Description (47) Helps to organize the information mapping of storage and processors. In a specific embodiment, the SAN gateway is made 8 1 0 to maintain A virtual private mapping that connects the number of logical units or other storage targets to the host attached to the SCSI. SAN gateway production 8 10 also maintains a connection storage disk component and type information, Channel information, target identifier, LUN information, and continuous component mapping of the unit identifier, thus providing a basic mapping of available components in the system. SAN Gateway 810 also maintains a connection between the SCSI channel number and the target identifier, The SCSI mapping of the LUN identifier and the component identifier shows that the target storage disk unit is currently mapped to the SCSI channel. Referring again to Figure 8, most utility methods or subroutines are provided, including storage disks. Copy Utility 832, Storage Disk Placement Utility 834, Storage Disk Integration Utility 83 6, Storage Disk Configuration Utility 83 8, and SAN Gateway Utility 840. Storage Disk Copy Utility 832 is used to copy an Tied volume to another unbound volume. The storage disc placement utility 834 is used to manually place a set of volumes; for example, it can be used to place a primary volume that is not associated with a virtual server farm. Storage discs Combination Utility 83 6 is used to manually combine a set of volumes to the main volume. Storage Disk Configuration Method 8 3 8 is used to manually form or interrupt a set of interlocking volumes. The SAN Gateway Utility 840 directly triggers manual control of SAN Gateway 3 06. 3.6 Volume Wide Area Namespace The above configuration supports storage disc volumes Wide-area name space. In this configuration, different processors can read data from the storage disk volume at the block level. 50 I ----.-- Cloth II (Please read the precautions on the back before filling (This page)-, 1T This paper size applies the Chinese National Standard (CNS) A4 specification (210 × 297 mm) 1231442 A7 B7 Printed by the Consumers ’Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs 5. Description of the invention (48) Of storage dish volume. As a result, different hosts of the virtual server farm can access the shared content at the file level or the block level. The ability to access from the same time to have the same block memory elements can benefit many applications. For example, it contains aggregate database applications, aggregate file systems, and so on. The mentioned application by Aziz et al. Used field validation language to reveal the symbol definition of the virtual server field, and used the &lt; storage disk / storage disk &gt; tag to specify the storage in the field validation language. However, in its disclosure, the storage disc labels all assigned block storage discs specific to the server given. That needs to indicate that the storage disk components given by the &lt; storage disk / storage disk &gt; label in the validation language should be shared among a group of servers in a particular virtual server farm. In one approach, the field validation language includes a set of mechanisms to indicate that a set of LUNs will be shared among a set of servers and given a grid control plane. In the first argument of this method, as shown in the instruction example in Table 5, a virtual server farm is defined as a group of LUNs in a field wide area manner; instead of using storage disk labels to refer to storage disks on a per-server basis. Table 5-FML definition of wide-area presence LUNs &lt; farm fmlversion-? 1.2 &quot; &gt; &lt; farm -global-disks &gt; &lt; global-disk global-name = 'Oracle Cluster, partition Γ, 51 I ----.-- &quot; Γ · 装-(Please read the notes on the back before filling in this page) The size of the paper is applicable to China National Standard (CNS) A4 (210X297 mm) 1231442 A7 A7 B7 Economy Printed by the Intellectual Property Cooperative of the Ministry of Intellectual Property, V. Invention Description (49) drivesize = ，， 863r〉 &lt; global-disk global- name =, Oracle Cluster, partition 2 &quot; »drivesize =` `863r &gt; &lt; / farm- global-disk> </ farm> In another argument of this method, as shown in the example of Table 5 instructions, the validation language is used to specify the field-wide-storage disk reference method from the given server and indicate how Use the &lt; Shared-Storage Disks &gt; tab described below to map a wide-area storage disk to a storage disk that is locally visible on the given server. Table 6-FML definition of LUNs in a server farm in a wide area &lt; server-role id = &quot; role37 "name =" serverl "&gt; &lt; hw &gt; cpu-sun4u-x4 &lt; / hw &gt; &lt; disktarget =” 0 ”drivetype =” scsi ”drivesize = M8631” &gt; <diskimage type = `` system ''> solaris &lt; / diskimage> <attribute name = `` backup-policy ”value = nnightly” / &gt; &lt; / disk &gt; &lt; shared-disk global-name = &quot; Oracle Cluster, partition r5, target = Ml drivetype = `` scsi "/ shared- disk &gt; &lt; shared- disk global-name = &quot; Oracle Cluster, partition 2 ,, , target = ,, 2 drivetype = ”scsi” / shared- disk &gt; &lt; / server-role &gt; In the example given above, the server-role definition display, with 52 paper standards applicable to Chinese national standards ( CNS) Α4 size (210X 297mm) I ----- · -1-1 ^-(Please read the precautions on the back before filling this page)

、 1T 1231442 A7 B7 V. Description of the invention (50) I ---- ^ ----- (Please read the precautions on the back before filling this page) &lt; Storage disc &gt; Servo for storage disc in the area specified by the label And two sets of storage disks that can be shared by other servers specified by the &lt; public-storage disk &gt; tag. As long as the wide-area-name of the public storage disc is the same as the wide-area-name identified by a set of wide-area storage discs in the <field-wide-storage-disc> list, it is mapped to &lt; public-storage The area indicated by the disc &gt; drives the target. To illustrate the virtual server farm in this way, the storage management subsystem of the grid control plane first installs all the farm-wide-area storage disks before any other storage disk processing procedures. Once these storage disks have been generated and placed using the procedures described in this document, the storage management subsystem processes all of the storage disk components in common in each server definition. Whenever a public storage disk component involves a wide-area visible storage disk, it is mapped to an appropriate indicator, as specified by the area-target tag. Different servers may then view the same portion of the block level memory as the same or different number of area targets. Printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs. By specifying different drive types, such as fiber-channel or iSCSI, different memory access mechanisms can be used to access the same portion of the block level memory. In the above example, "scsi" identifies the local SCSI bus as the storage access mechanism. This area SCSI bus is attached to the virtual storage layer described here. 4.0 Hardware Essentials Figure 9 is a block diagram showing a computer system 900 on which an embodiment of the present invention can be made. The computer system 900 includes a bus 902 or other communication mechanism for transmitting information, and a place for coupling information with the bus 902 for processing information. 53 This paper size applies to the Chinese National Standard (CNS) A4 specification (210X297 mm) A7 B7 1231442 5. Invention description (M) processor 904. The computer system 900 also includes a main memory 906, such as a random access memory (RAM) or other dynamic storage element, which is coupled to a bus 902 for storing information and instructions executed by the processor 904. The main memory 906 can also be used to store temporary variables or other intermediate information when the processor 904 executes instructions. The computer system 900 further includes read-only memory (ROM) 908 or other static storage elements coupled to a bus 902 for storing static information and instructions of the processor 104. A storage element 910, such as a magnetic disk or optical disk, is provided and coupled to a bus 902 for storing information and instructions. The computer system 900 may be coupled to a display 9 1 2 via a bus 902, for example, a cathode ray tube (CRT) for displaying information to a computer user. An input element 914 containing alphanumerics and other keys is coupled to a The information and command selection is transmitted to the bus 902 of the processor 904. Another type of user input element is a cursor controller 9 1 6 such as a mouse, a trackball, or a cursor direction key for transmitting direction information and command selection to the processor 904 and for controlling cursor movement on the display 912. . This input element can have two degrees of freedom in the first axis (for example, the X axis) and the second axis (for example, the y axis), which allows the element to specify a position on a plane. This invention relates to the use of computer system 900 for computer system symbol definitions. According to an embodiment of the present invention, the symbol definition of the computer system is provided by the computer system 900 in response to the processor 904 executing one or more sequences of one or more sets of instructions contained in the main memory 906. . These instructions can be read into the main memory 906 from another computer-readable medium, such as the storage element 9 10. Included in the main memory 906 refers to 54 paper sizes applicable to the Chinese National Standard (CNS) A4 specifications (21 × 297 mm) (Please read the precautions on the back before filling out this page) Printed by the property bureau employee consumer cooperative 1234142 A7 B7 V. Description of the invention (52) The execution of the order sequence causes the processor 904 to perform the processing steps described herein. In other embodiments, 'hard-wired circuits may be used to implement the invention in place of or in combination with software instructions. Therefore, the embodiments of the present invention are not limited to any specific combination of hardware circuits and software. The term "computer-readable media" as used herein indicates any media involved in providing instructions to processor 904 for execution. These media can take many forms, including, but not limited to, non-perishable media, evanescent media, and transmission media. Non-erasable media includes, for example, optical or magnetic disks, such as storage element 9 1 0. Evanescent media contains dynamic memory, such as main memory 906. The transmission medium includes a coaxial cable, a copper wire, and an optical fiber 'which includes wiring including a bus 902. Transmission media can also take the form of sound or light waves, such as those generated by radio waveforms and infrared data communications. Common forms of computer-readable media include, for example, floppy disks, flexible disks, hard disks, magnetic tapes, or any other magnetic media, CD-ROM, any other optical media, punched cards, paper tape, holes Hole-type any other actual media, RAM, PROM, and EPROM, flash-EPROM, any other memory chip or cassette, carrier wave as described here, or any other computer readable media. Various forms of computer-readable media can be used to carry one or more sequences of one or more sets of instructions to the processor 904 for execution. For example, the instructions may initially be carried on a remote computer diskette. The remote computer can load the instructions into its dynamic memory and use modems via a telephone line to transmit the instructions. The area modem of computer system 9 0 can receive telephone lines 55 This paper size is applicable to China National Standard (CNS) A4 specification (210X297 mm) I ---- · -1 Clothes-(Please read the note on the back first (Fill in this page again)

Printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs of the 1T 1231442 A7 B7 V. Description of the invention (53) The above information is used and an infrared transmitter is used to convert the information into an infrared signal. The infrared detector can receive the information carried in the infrared signal and appropriate circuits can be placed on the bus 902. The bus 902 carries data to the main memory 906, and the processor 904 obtains and executes the instruction. The instructions received by the main memory 906 can be stored on the storage element 9 10. The computer system 900 also includes a communication interface 918 coupled to the bus 902. The communication interface 918 provides two-way data communication coupled to a network link 920, which is connected to a local area network 922. For example, the communication interface 918 is an ISDN card or modem to provide data communication connection to a corresponding type of telephone line. In another example, the communication interface 9 1 8 may be a local area network (LAN) card to provide data communication connection to a compatible LAN. Wireless links can also be made. In any of these productions, the communication interface 9 1 8 transmits and receives electrical, electromagnetic, or optical signals that carry digital data streams representing various types of information. Network link 920-generally provides data communication to other data components through one or more networks. For example, the network link 920 may provide a connection to a host computer 924 or a data device operated using an Internet service provider (ISP) 926 via a local network 922. ISP 926 then provides data communication services via a global packaged data communication network commonly referred to as the "Internet" 928. Both LAN 922 and Internet 928 use electrical, electromagnetic, or optical signals that carry digital data streams. The signals via various networks and the signals on the network link 9200 and via the communication interface 918 are exemplary forms of carrier for carrying information. 56 This paper size applies the Chinese National Standard (CNS) A4 specification (210X 297 mm) ------- II1 · Install II (please read the precautions on the back before filling this page),? Τ Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 B7 V. Description of Invention (54) Computer System 900 It can send messages and receive data including program instructions via the network, network link 920, and communication interface 9 1 8. In the example of the Internet, the server 930 may pass the Internet 928, ISP 926, and LAN 922. And the communication interface 918 to transmit the instructions required by the application. According to the present invention, a set of such downloaded applications provides the symbol definitions of the computer system as described herein. When The processor 904 can execute the received instructions when the instructions are received or stored in the storage element 9 10 or other non-ephemeral memory for later execution. In this manner, the computer system 900 can use a carrier wave form The application instructions are obtained. 5.0 Extensions and Changes In the foregoing description, the present invention has been described with reference to specific embodiments thereof. However, it is apparent that various modifications and changes can be made therein without departing from the spirit and scope of the present invention. The instructions and graphics are only for display and display without restriction. (Please read the notes on the back before filling this page) China National Standard (CNS) A4 specification (210X297 mm) 1231442 A7 A7 B7 Printed by the Consumer Cooperatives of the Intellectual Property Bureau of the Ministry of Economic Affairs 5. Description of the invention (55) Comparison table of component numbers 120 ... Customer 122 ... Execution Browser 12 4 ... Internet 126 ... Service Provider 128 ... Graphical User Interface Editor Server 130 ... Management / Management Server 132 ... Partial Computing Barrier 13 1 ... database 13 4 ... data center 135 ... control plane database 2 0 2 ... network 2 04 ... firewall 206 ... load balancer 208a, 208b, 208c ... CPU component 210 ... Storage area network gateway 212 ... Area network 2 14a, 2 14b ... Disk array [J 3 02A, 302B, 3 02C , 3 02N ... host 304A, 304B, 3 04N ... storage unit 306 ... storage gateway 3 08 ... storage area network 3 10 ... virtual storage layer 58 I- --- · --T &quot; &quot; · Install-- (Please read the notes on the back before filling this page) The size of the paper is applicable to the Chinese National Standard (CNS) A4 (210X 297 mm) 1231442 A7 B7 5 、 Explanation (56) 3 12 …… Control processor (please read the precautions on the back before filling this page) 320A, 320B, 320C ... Control [J processor 322 ... control database 324 ... storage management 326 ... field manager 3 3 0 ... local area network 3 3 0D ... SCSI channel 340 ... virtual storage element 342D ... SCSI target connection 344 ... RAM cache 346 ... optical fiber Channel storage area network 348 ... Link 401 ... control network 404A ... disk array 404B ... storage unit 406A ... disk array controller 406B ... disk array controller 408 ... network attached storage network 410 ... Printed by the Consumer Cooperative of the Intellectual Property Bureau of the Ministry of Mobile Economy 4 12A, 4 12B, 4 12N ... Switch 4 14A, 4 14B ... Data switch 416 ... Link 5 10 ... Network link 5 12 …… Port table with optical fiber 59 This paper size applies Chinese National Standard (CNS) A4 (210X297 mm) Printed by the Consumer Cooperative of Intellectual Property Bureau of the Ministry of Economic Affairs 1231442 A7 B7 V. Description of the invention (57 ) 5 14 ...... Disk table optical fiber with port table 516 ... Disk combination table 6 0 2 ...... smells 60 4 ... clip manager 606 ... field manager 6 0 8 ... ... host 610 ... operating system image 7 0 2 ... free state 704 ... placement state 7 08 ... manufacturing conversion volume transfer 7 0 9 ... car special shift 710 ... configuration state 7 11 ... Transfer 7 12 ... Combined with failover 714 ... Unconfigured state 716 ... Combined with state 718 ... Map failover 7 2 0 ... ... unbound state 7 2 1 ... disk array combined transition 724 ... mapped state 726 ... split / joined transition 7 2 8 ... unmapped state 7 3 0 ... delete transfer 73 1 ... abort transfer-volume transfer 60 This paper size applies Chinese National Standard (CNS) A4 (210X297 mm) (Please read the precautions on the back before filling this page)

1231442 A7 B7 V. Description of the invention (58) (Please read the precautions on the back before filling out this page) 802 ... field manager wiring category 804 ... SAN structure interface 806 ... SAN structure production 808 ... SAN gateway interface 810 ... S AN gateway production 812 ... Storage manager service layer 814 ... Storage manager connection section 8 16 ... Requires 818 ... Storage manager requires processor 820 ... Requirement Processor 822 ... storage integration layer program 824 ... storage manager type 83 2 ... storage disk copy utility 834 ... storage disk placement utility 8 3 6 ... storage disk combined with utility program 83 8 ... storage disk Configuration Utility 840 ... SAN Gateway Utility 900 ... Computer System 902 ... Printed by Employee Consumer Cooperatives, Intellectual Property Bureau, Ministry of Bus Economy 904 ... Processor 906 ... Main Memory 908 ... Read Only Memory (ROM) 910 ... storage element 912 ... display 61 This paper size applies to the Chinese National Standard (CNS) A4 specification (210X297 mm) 1231442 A7 B7 Description of the invention (59) 9 14 ···… input element 9 16 ·. ·… Standard control 918 ..… Communication interface 920… Network link 922… LAN 924… Host computer 926 &quot;.… Internet service provider (ISP) 928… Internet 93 0 &quot;.… Server (Please read the notes on the back before filling out this page) Printed on the paper by the Consumers' Cooperative of the Intellectual Property Bureau of the Ministry of Economic Affairs The paper size is applicable to China National Standard (CNS) A4 (210X297 mm)

Claims (1)

ABCD 1231442 VI. Scope of patent application 1. A method for selectively configuring a memory to a processor, which includes computer manufacturing steps: receiving a request to place the memory to the processor; and configuring a virtual storage layer to logically One or more sets of logical units are connected from one or more sets of storage units to the processor. 2. For the method in the first scope of patent application, wherein the configuration step is implemented without modifying the operating system of the processor. 3. The method according to item 1 of the patent application scope, wherein the configuration step is implemented using a control processor coupled to a plurality of storage gateways via one or more storage networks, such storage gateways It is coupled to one or more sets of storage units via the storage network. 4. The method according to item 1 of the patent application scope, wherein the configuration step further includes the steps of: configuring a storage gateway in the virtual storage layer to map the logical unit to the boot port of the processor; and configuring a Group or groups of memory units for processor access to logical units. 5. The method of claim 1, wherein the virtual storage layer includes a control processor coupled to a storage gateway via a storage network, wherein the storage gateway is coupled to a group or via a storage network. A plurality of sets of memory units, and the configuration step further includes the steps of: the control processor sends instructions to the memory gateway to map the logic unit to a boot port of the processor; and the control processor sends instructions to Memory unit for processor access _ 63 Too large paper size applies Chinese National Standard (CNS) A4 specification (210X 297 mm) ------.-- 1 · Packing II (Please read the precautions on the back before (Fill in this page) Ordered by the Ministry of Economic Affairs, the Ministry of Economic Affairs and the Consumer Financial Cooperatives 8 8 8 8 ABCD Printed by the Ministry of Economic Affairs, the Ministry of Economics and Financial Consumers Cooperatives 1231442 々, the scope of patent application to one or more logical units 6 · The method according to item 1 of the patent application scope, wherein the configuration step further includes the steps of: receiving a request to place a storage device in a control processor coupled to the storage gateway via a storage network, wherein the storage The server gateway is coupled to one or more sets of storage units via a storage network; the storage gateway is instructed to map one or more sets of logical units to a boot port of the processor; and the one or more sets of storage are instructed Processor unit for the processor to access one or more sets of logical units. 7. The method of claim 1 in the scope of patent application, wherein: the method further includes the steps of storing first information connecting the processor to the logic unit and second information connecting the logic unit to the memory unit, and the The configuration step further includes a step of reconfiguring the virtual storage layer based on the stored first information and second information to logically couple the one or more sets of logical units to the boot port from one or more sets of The group of memory units maps the one or more sets of logical units to a boot port of the processor. 8. The method of claim 1 further includes the steps of generating a request for a storage processor to be communicatively coupled to the control processor of the control database, wherein the request is directed from the control processor to the communication A storage manager that is ground-coupled to the control processor, the control database, and the storage network including the storage disk gateway, and wherein the step of configuring the virtual storage layer includes: reconfiguring the storage disk _____ 64 The scale is applicable to China National Standard (CNS) A4 (210X 297mm) (Please read the precautions on the back before filling this page) 1231442 A8 B8 C8 D8 VI. Scope of Patent Application Road to logically couple one or more sets of logic units to the processor's boot port. 9. The method of claim 8 further comprising the steps of: issuing a command from the storage manager to one or more sets of storage units so that the processor can access one or more sets of logical units. 1 〇. The method of claim 1, wherein the configuration step further includes the steps of: identifying one or more sets of logic of one or more sets of storage units having a sufficient storage quantity to meet the requirement Unit (LUN); indicates the storage gateway in the virtual storage layer to map the identified LUN to the processor's small computer system interface (SCSI) port zero based on the unique processor identifier; and indicates the group or Multiple sets of storage units for a processor with a unique host identifier to access the identified LUN. 1 1. The method according to item 1 of the patent application scope, wherein the configuration step comprises: issuing a request to place one or more sets of volumes on one of the one or more sets of storage units; issuing a request to Use one or more groups of disposed volumes to form an interlocked volume; configure the interlocked volumes for use with a processor; issue a first instruction to one or more groups of storage units to allow the processor to store Take the linked volume and combine the processor to the linked volume; issue a second instruction to the gateway in the virtual storage layer to combine the linked volume to the processor. 65 This paper size applies to China National Standard (CNS) A4 specification (210X297 mm ------ ^-7 · &quot; ^^-(Please read the precautions on the back before filling this page), 11 The total wealth of the Ministry of Economic Affairs is: 0: printed by the industrial and consumer cooperatives 1231442 A8 B8 C8 D8 VI. Application for patent scope 1 2. For the method of applying for patent scope No. 11 further steps include: The second instruction cannot combine the linked volume to the processor; the third instruction is issued to one or more sets of storage units to separate the processor from the linked volume. 1 3. If the method of item 11 of the scope of patent application, it The steps further include: determining that the first instruction cannot be combined with the processor to the linked volume; issuing a fourth instruction to one or more sets of storage units to interrupt the linked volume. 1 4. If the scope of the patent application The method of item 1, wherein the one or more sets of logical units associated with the processor include at least one set of logical units of the first volume of the one or more sets of storage units, and the at least one or more sets of storage The second volume in the unit A set of logical units. 1 5. As the method of the scope of the patent application, the method of placing the storage device specifies some storage devices to be placed. 1 6. The method of the scope of the patent application, the method of item 1, wherein The requirements for the placement storage specify the type of storage to be placed. 1 7. —A method to selectively connect the storage to the main processor without modifying the main operating system, which includes the steps of: receiving the connection storage A requirement at a virtual storage layer coupled to a plurality of storage units and to one or more sets of main processors, wherein the request identifies a specific set of main processors and the number of required storages; configures the virtual storage Layer in order to have _____66 from the number of required storage units. I paper size applies Chinese National Standard (CNS) A4 specification (210X297 mm) ------, ---- (Please read the precautions on the back before (Fill in this page), 1T Smart Ministry of Economic Affairs &gt; Printed by t-QM Industrial and Consumer Cooperatives 1231442 A8 B8 C8 D8 Smart Ministry of Economics and Finance ^ ;: Only printed by Industrial Consumer Cooperatives VI. Patent Application Scope!! | 23 . A device for defining and deploying a networked computer system, comprising: a device for receiving a request to couple a storage to a specific host processor in a virtual storage layer coupled to a plurality of storage units, wherein the request Specify the number of required memory; use the reconfigured virtual storage layer to logically couple one or more sets of logical units to the standard boot port of a specific host processor, and use it from the majority with the required number of memory A device that maps one or more sets of logical units to the standard boot port of a specific host processor. 24. An apparatus for defining and deploying a network computer system, comprising: a set of processors; a set of computer-readable media, which can be accessed by the processor and store the network computer according to a structural markup language This text indicates the system logic configuration; one or more sets of instruction sequences stored in a computer-readable medium, and when executed by a processor, the steps that cause the processor to perform are: receiving an associated memory to a specific A host processor request, wherein the request is received in a virtual storage layer coupled to a plurality of storage units, wherein the request specifies the number of required storages; a virtual storage layer is reconfigured to logically couple a One or more sets of logic units are mapped to the boot port of a specific host processor, and one or more sets of logic units are mapped to the standard boot port of a particular host processor from a plurality of memory units having a required number of memories. — _69 This paper size applies to China National Standard (CNS) A4 specification (210X297 mm), --------- Order ----- (Please read the precautions on the back before filling this page) 1231442 A8 B8 C8 D8 VI. Patent application 25. — A system for selectively connecting storage to the main processor, which includes = a set of virtual storage mechanisms that are coupled to a plurality of storage units and to a set Or multiple sets of main processors; a set of control processors communicatively coupled to the virtual storage mechanism and containing a set of computer-readable media carrying one or more sets of instruction sequences, when the instruction sequence is When multiple sets of processors are executed, the steps that lead to one or more sets of processors are: receiving a request to associate storage with a specific host processor, where the request identifies the amount of storage required; using reconfiguration virtual The storage mechanism logically couples one or more sets of logical units to a standard boot port of a specific host processor, and maps one or more sets of logical units from a storage unit having a required number of storage units Standard specific master boot port processors. 26. The system of claim 25, wherein the control processor is coupled to the plurality of storage gateways through one or more storage networks, and the plurality of storage gateways are connected through one or more storage gateways. A bank of storage networks is coupled to a plurality of storage units. 27. The system of claim 25, wherein the control processor is coupled via a storage network to a storage gateway coupled to the plurality of storage units via the storage network, and wherein the control processor The instruction sequence further includes instructions. When it is executed by one or more processors, the steps leading to one or more processors are: _ 70._ This paper standard is applicable to China National Standard (CNS) A4 Specifications (210X297 mm) I --------- Order ------- (Please read the precautions on the back before filling out this page) 1231442 A8 B8 C8 D8 Ministry of Economic Affairs 4: 9: Printed by the Industrial and Consumer Cooperatives 6. Application for patents ranges from the control processor to instructions to the memory gateway to map one or more sets of logical units to a specific main processor A standard bootup; and issuing instructions from the control processor to a plurality of memory units to enable the particular host processor to access one or more sets of logic units. 28. The system of claim 25, wherein the control processor is communicatively coupled to a set of control data bases, the control data bases including the first information connecting the host to the logic unit and the logic unit to the storage unit And the second information of the control processor further includes instructions that, when executed by one or more processors, cause the one or more processors to perform steps according to the first information: And the second information uses a reconfigured virtual storage mechanism to logically couple one or more sets of logical units to a standard boot port of a particular host processor, and from a plurality of storage units having the required number of storage units A standard boot port that maps one or more logical units to a specific host processor. 29. If the system of claim 25 is applied for, the instruction sequence of the control processor further includes instructions. When it is executed by one or more groups of processors, the steps leading to one or more groups of processors are: : Identifies one or more logical units (LUNs) of the plurality of storage units with the required storage quantity; instructs a group of storages in the virtual storage layer to smell to map the identified LUNs based on the unique host identifier The small computer system interface (SCSI) port to a specific host processor is zero; and __71_ is indicated for a plurality of storage units so that it has a unique host identifier. This paper size applies to the Chinese National Standard (CNS) A4 specification (210X 297 male) (%) Ί. Order (please read the notes on the back before filling out this page) 8 8 8 8 ABCD 1231442 6. The main processor with specific patent application scope accesses to the identified LUN. 30. The system of claim 25, wherein the instruction sequence of the control processor further includes instructions that, when executed by one or more processors, cause steps performed by one or more processors. Yes: Issue a request to place one or more sets of volumes on one of the plurality of storage units with the required number of storage units; issue a use of one or more placed volumes to achieve a set of interlocking volumes A set of requirements; configuring the chained volume for use with a particular host processor; issuing a first instruction to a plurality of storage units to combine the specific volume with a particular host processor allowing access to the chained volume From the main processor to the linked volume; issue a second instruction to the gateway in the virtual storage layer to combine the linked volume to the specific main processor. 31. The system of claim 25, wherein the instruction sequence of the control processor further includes instructions that, when executed by one or more processors, cause one or more processors to perform The steps are: determining that the second instruction cannot combine the linked volume to the specific main processor; and issuing a third instruction to the plurality of storage units to separate the specific main processor from the linked volume. 32. The system of claim 25 in the scope of patent application, wherein the instruction sequence of the control processor further includes instructions, when it is processed by one or more groups --- 72_ This paper standard is applicable to China National Standard (CNS) A4 Specifications (210X297 mm) (Please read the notes on the back before filling out this page) Order Lf Wisdom of the Ministry of Economic Affairs, printed by 1213442 A8 B8 C8 D8 of the Consumer Cooperative Cooperative 6. Scope of Patent Application ------ , I installed-(Please read the precautions on the back before filling out this page) When the processor is executed, it causes one or more groups of processors to make a decision. The first instruction cannot be combined with the specific main processor to the chained volume. Step; Issue a fourth instruction to the plurality of storage units to interrupt the interlocking volume. 33. —A method of selectively arranging storage to a processor 'which includes computer-made steps including: receiving a set of requests to place a storage in the processor; and logically from one or more sets of storage units Scheduling one or more sets of logical units to the processor, wherein the one or more sets of logical units include at least one set of logical units of a first volume in the one or more sets of storage units and the one At least one set of logical units of a set of second volumes in one or more sets of storage units. 3 4. The method according to item 1 of the patent application scope, wherein the configuration step is implemented using a switching element in a storage area network. 35. The method according to item 1 of the scope of patent application, wherein the configuration step is implemented using a storage disk array in a storage area network. Ministry of Economy Wisdom! Choi 4- ^ 9 Printed by Industrial and Consumer Cooperatives 3 6. The method of claim 1 in the patent application scope, wherein the one or more sets of logical units connected to the processor include at least one set of logical units' the at least one set of logic The unit includes a set of first volumes of the reservoirs in the first storage unit and a set of second volumes of the reservoirs in the second storage unit. 37. —A method of selectively configuring storage to a processor 'includes computer-made steps including: receiving a symbol definition of a virtual server farm containing a storage definition; generating a storage storage to the storage according to the storage definition' One of the processors _____23_ This paper size is applicable to China National Standard Engine (CNS) A4 specification (210X 297 public shame) 1231442 A8 B8 C8 D8 patent application scope!?!! Group requirements; and configure a set of virtual storage layer to start from One or more sets of storage units are logically connected to the processor. 38. The method of claim 37, wherein the storage definition identifies the number of storage required and the SCSI target for the storage. 39. The method of claim 37, wherein the storage definition identifies the number of storage required and the file system set point for the storage. 40. The method of claim 1, wherein the one or more sets of storage units are configurable storage units. 41. The method according to item 1 of the patent application scope, wherein the configuration virtual storage layer includes dynamically connecting one of the processors from one or more memory units with a specified service quality to one or more groups Steps in a logical unit. 42. The method of claim 1, wherein the step of configuring a virtual storage layer includes: dynamically connecting a port of a processor with a port from a group or groups of storage units having a specified service quality. Groups or groups of logical units without involving or affecting the operating system of the processor. (Please read the precautions on the back before filling out this page) Order Lf Ministry of Economic Affairs, Intellectual Property, Printed by 工 Μ 工 合作 工 合作社 隼 隼 家家 家 国 中用 用 1 1 Imin 74% Public 7 9 2