Storage system, storage service system, storage processing method and storage server

Abstract

The invention provides a storage system, a storage service system, a storage processing method and storage servers, and relates to the field of storage, and at least two storage servers can be arranged in the storage system. Wherein the storage servers synchronously store the same user data; moreover, each storage server is provided with an HBA virtual port with the same storage area network identifier, and the binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client is established, so that the seamless switching between the master and the standby is realized. In actual work, the main server can utilize the HBA virtual port of the main server to carry out storage service interaction with the client; according to the technical scheme, the standby server needs to forbid the HBA virtual port of the standby server, the standby server can be automatically upgraded to the main server when detecting that the main server breaks down, storage service interaction is carried out with the client side based on the HBA virtual port of the standby server, and therefore dual-machine hot standby can be achieved through the storage server, and cost can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of storage, and in particular to a storage system, a storage service system, a storage processing method and a storage server. Background Art

[0002] As users' data storage needs continue to grow, storage area networks (SANs) have emerged. They can use mesh channel technology to connect storage servers through switches to establish a regional network dedicated to data storage. Common storage area networks include FC-SAN (Fiber Channel- Storage Area Network, SAN network using fiber channel), which connects clients and storage systems through fiber channels and transmits data through fiber channels.

[0003] In the related art, to ensure high availability, storage area networks generally implement dual-machine hot standby. However, in the related art, the storage area network usually consists of a storage virtualization gateway between the client and the storage server responsible for the access, management, and data forwarding of storage services. In order to achieve dual-machine hot standby, multiple storage virtualization gateways need to be introduced to solve the single point failure problem. This not only increases the deployment cost, but also increases the complexity of the storage area network and reduces the stability of the storage area network. Summary of the invention

[0004] The purpose of the present invention is to provide a storage system, a storage service system, a storage processing method and a storage server, which can realize dual-machine hot standby by the storage server itself without introducing multiple storage virtualization gateways, thereby reducing the deployment and operation and maintenance costs of the storage area network.

[0005] In order to solve the above technical problems, the present invention provides a storage system, which includes at least two storage servers; the storage servers synchronously store the same user data, are provided with HBA virtual ports with the same storage area network identifier, and are provided with a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client; the storage servers include a backup server and a main server;

[0006] The master server is used to activate its own HBA virtual port and perform storage service interaction with the client based on its own HBA virtual port and the binding relationship;

[0007] The standby server is used to disable its own HBA virtual port and detect whether the main server is faulty; when it is determined that the main server is faulty, it is upgraded to the main server, activates its own HBA virtual port, and interacts with the client for storage services based on its own HBA virtual port and the binding relationship.

[0008] Optionally, the storage servers jointly form a DRDB cluster, and synchronously save the same user data based on the DRDB cluster.

[0009] The present invention also provides a storage service system, comprising: a client, the storage system as described above, and a FCSAN network, wherein the FCSAN network is arranged between the client and the storage system, and the FCSAN network comprises a fiber switch;

[0010] The fiber switch is provided with a correspondence between the storage area network identifier of the HBA virtual port in the storage system and the storage area network identifier of the client, and is used to transfer storage service interaction data between the client and the HBA virtual port according to the correspondence.

[0011] The present invention also provides a storage processing method, which is applied to any storage server in the storage system as described above, and the method comprises:

[0012] When determining that it is the main server, activating its own HBA virtual port, and performing storage service interaction with the client based on the binding relationship between its own HBA virtual port, the storage area network identifier of the HBA virtual port and the storage area network identifier of the client;

[0013] When it is determined that it is a backup server, it disables its own HBA virtual port and detects whether the main server is faulty; when it is determined that the main server is faulty, it is upgraded to the main server, activates its own HBA virtual port, and interacts with the client for storage services based on its own HBA virtual port and the binding relationship.

[0014] Optionally, it also includes:

[0015] When it is determined that it is the main server, if it is determined that it has recovered from the fault state to the normal state, it will disable its own HBA virtual port and downgrade to the standby server.

[0016] Optionally, the storage servers jointly form a DRDB cluster, and synchronously save the same user data based on the DRDB cluster;

[0017] The method further comprises:

[0018] When determining that it is the primary server, it sets itself as the host of the DRDB cluster;

[0019] When it is determined that it is a backup server, it sets itself as a backup machine of the DRDB cluster; when it is upgraded to the main server, it switches itself to the main machine of the DRDB cluster.

[0020] Optionally, it also includes:

[0021] When determining that the server itself is a master server, creating a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client, and recording the binding relationship in a configuration file;

[0022] The configuration file is synchronized to all the standby servers.

[0023] Optionally, it also includes:

[0024] When it determines itself as the primary server, it periodically outputs heartbeat signals;

[0025] The detecting whether the main server fails comprises:

[0026] When it is determined that the server is a standby server, it detects whether the main server is faulty through the heartbeat signal sent by the main server.

[0027] Optionally, it also includes:

[0028] Creating the HBA virtual port based on its own HBA physical card and a preset storage area network identifier;

[0029] A storage area network server is created based on the HBA virtual port.

[0030] The present invention further provides a storage processing device, which is applied to any storage server in the storage system as described above, and the device comprises:

[0031] The main server service module is used to activate its own HBA virtual port when determining that it is the main server, and perform storage service interaction with the client based on the binding relationship between its own HBA virtual port, the storage area network identifier of the HBA virtual port and the storage area network identifier of the client;

[0032] The backup server business module is used to disable its own HBA virtual port and detect whether the main server is faulty when it is determined that it is a backup server; upgrade to the main server when it is determined that the main server is faulty, activate its own HBA virtual port, and interact with the client for storage business based on its own HBA virtual port and the binding relationship.

[0033] The present invention also provides a storage server, comprising:

[0034] Memory for storing computer programs;

[0035] A processor is used to implement the storage processing method as described above when executing the computer program.

[0036] The present invention also provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are loaded and executed by a processor, the storage processing method described above is implemented.

[0037] The present invention provides a storage system, which comprises at least two storage servers; the storage servers synchronously store the same user data, are provided with HBA virtual ports having the same storage area network identifier, and are provided with a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of a client; the storage servers comprise a standby server and a main server; the main server is used for activating its own HBA virtual port, and performing storage service interaction with the client based on its own HBA virtual port and the binding relationship; the standby server is used for disabling its own HBA virtual port, and detecting whether the main server fails; when it is determined that the main server fails, the standby server is upgraded to the main server, activates its own HBA virtual port, and performs storage service interaction with the client based on its own HBA virtual port and the binding relationship.

[0038] It can be seen that the storage system in the present invention includes at least two storage servers, and these storage servers can be further divided into backup servers and main servers. Among them, each storage server synchronously stores the same user data; and each storage server is provided with an HBA virtual port with the same storage area network identifier, and a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client is provided. In this way, when performing the master-slave switch, it can be ensured that the client does not perceive the backend changes, and the master-slave seamless switch can be achieved. In the process of executing the actual storage business, the main server can activate its own HBA virtual port, and interact with the client for storage business based on its own HBA virtual port and binding relationship. The backup server needs to disable its own HBA virtual port and detect whether the main server is faulty. If it is determined that the main server is faulty, the backup server automatically upgrades to the main server, activates its own HBA virtual port, and interacts with the client for storage business based on its own HBA virtual port and binding relationship. In this way, dual-machine hot standby can be achieved only by the storage server, without the need to introduce an additional storage virtualization gateway, which can effectively reduce the deployment and operation and maintenance costs of the storage area network. The present invention also provides a storage service system, a storage processing method, a storage server and a computer-readable storage medium, which have the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0040] Figure 1 A schematic diagram of an existing storage area network provided by an embodiment of the present invention;

[0041] Figure 2 A schematic diagram of the structure of a storage service system provided by an embodiment of the present invention;

[0042] Figure 3 A flowchart of a storage processing method provided by an embodiment of the present invention;

[0043] Figure 4 A structural block diagram of a storage processing device provided by an embodiment of the present invention;

[0044] Figure 5 A structural block diagram of a storage server provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] As users' data storage needs continue to grow, storage area networks (SANs) have emerged. They can use mesh channel technology to connect storage servers through switches to establish a regional network dedicated to data storage. FCSAN (Fiber Channel Storage Area Network, SAN network using fiber channel) is a common storage area network that can use fiber channel and fiber switches to connect clients and storage systems to ensure data transmission speed.

[0047] In the related technologies, to ensure high availability, storage area networks generally implement dual-machine hot standby. However, in the related technologies, storage area networks are usually responsible for storage service access, management, and data forwarding by storage virtualization gateways between clients and storage servers. To achieve dual-machine hot standby, multiple storage virtualization gateways need to be introduced to solve the single point of failure problem. For easier understanding, please refer to Figure 1 , Figure 1 The present invention provides a schematic diagram of an existing storage area network, which includes a storage system 1, a client 2, a fiber switch 3 and a storage virtualization gateway 4. The storage system 1 includes multiple storage servers 10. Optical fibers 5 are provided between the client 2 and the fiber switch 3, and between the storage server 10 and the fiber switch 3. The storage virtualization gateway 4 is connected to the client 2 via Ethernet 6, and is connected to the fiber switch 3 via the optical fiber 5. When executing storage services, the storage virtualization gateway 4 is responsible for access, management and data forwarding. In this structure, in order to achieve dual-machine hot standby, at least two storage virtualization gateways 4 need to be added, and each needs to be equipped with at least two HBA cards (Host Bus Adapter) to solve the single point failure problem, and the cost of environment construction is high. In addition, after introducing multiple storage virtualization gateways 4, the storage area network will increase multiple network nodes, which will increase the risk of network stability. At the same time, the operation and maintenance personnel need to perform additional maintenance and routine inspections on each storage virtualization gateway 4, which increases the learning and operation and maintenance costs.

[0048] In view of this, in order to realize the dual-machine hot standby function in a storage area network at low cost, the present invention can provide a storage system, in which the storage server can realize the dual-machine hot standby by itself, without introducing multiple storage virtualization gateways, thereby reducing the deployment and operation and maintenance costs of the storage area network.

[0049] For easier understanding, please refer to Figure 2 , Figure 2 A schematic diagram of the structure of a storage service system provided by an embodiment of the present invention. Figure 2 In the embodiment of the present invention, the storage system 1 provided by the embodiment of the present invention includes at least two storage servers 10. The storage server 10 is connected to the client 2 through the optical fiber 5 and the optical fiber switch 3, and the Ethernet 6 is arranged between the storage servers 10. The storage server 10 synchronously stores the same user data, is provided with an HBA virtual port with the same storage area network identifier, and is provided with a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client 2; the storage server 10 includes a backup server and a main server. There can be one main server.

[0050] The master server is used to activate its own HBA virtual port and perform storage service interaction with the client based on its own HBA virtual port and the binding relationship;

[0051] The standby server is used to disable its own HBA virtual port and detect whether the main server is faulty; when it is determined that the main server is faulty, it is upgraded to the main server, activates its own HBA virtual port, and interacts with the client for storage services based on its own HBA virtual port and the binding relationship.

[0052] In the above system, in order to realize the dual-machine hot standby function reliably and at low cost, the following improvements are made:

[0053] 1. Set up at least two storage servers in the storage system, and set up a communication mechanism between the storage servers to ensure that the storage servers can communicate with each other. For example, Ethernet can be set up between the storage servers.

[0054] 2. The same user data is saved synchronously in each storage server. That is, the user data saved in each storage server is the same; and if the user data is updated in a storage server, the updated data will be synchronized to all storage servers.

[0055] 3. Set up an HBA virtual port with the same storage area network identifier in each storage server, and set up a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client. Among them, the HBA virtual port and the binding relationship are used for data transmission with the client. The HBA virtual port needs to be created based on the HBA physical card in the storage server; the storage area network identifier can be a WWN identifier (World Wide Name). After such a setting, when the active-standby switching is performed, since the HBA virtual ports in each storage server have the same storage area network identifier, the client will not feel the change of the HBA virtual port, and the business between the client and the storage server will not be interrupted, thereby ensuring the smoothness of the active-standby switching.

[0056] 4. The storage server includes a backup server and a main server. The main server is responsible for providing storage services to the client. It needs to activate its own HBA virtual port and interact with the client for storage services based on its own HBA virtual port and the above binding relationship. The backup server is responsible for providing hot standby services. It needs to disable its own HBA virtual port, that is, not respond to the client's storage service interaction; in addition, the backup server also needs to detect whether the main server is faulty, and when it is determined that the main server is faulty and cannot respond to the client, it will automatically upgrade to the main server, activate its own HBA virtual port, and interact with the client for storage services based on its own HBA virtual port and the above binding relationship.

[0057] It can be seen that through the above improvements, since the same user data is synchronously stored in the main server and the backup server, and both are provided with HBA virtual ports with the same storage area network identifier and the binding relationship between the HBA virtual port and the client, the main server and the backup server can be switched seamlessly. In addition, this embodiment also sets a main server failure detection mechanism for the backup server to ensure that the backup server can automatically upgrade to the main server when the main server failure is determined, and can realize automatic main-backup switching. Furthermore, it can avoid introducing multiple storage virtualization gateway devices in the storage area network, which can not only realize the hot standby function, but also reduce the complexity of the storage area network.

[0058] Furthermore, the storage servers may jointly form a DRDB cluster (Distributed Replicated Block Device), and may synchronously save the same user data based on the DRDB cluster. The primary server may be set as the primary of the DRDB cluster, and the backup server may be set as the secondary of the DRDB cluster.

[0059] Based on the above embodiments, the storage system in the present invention includes at least two storage servers, and these storage servers can be further divided into backup servers and main servers. Among them, each storage server synchronously stores the same user data; and each storage server is provided with an HBA virtual port with the same storage area network identifier, and a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client is provided. In this way, when performing the master-slave switch, it can be ensured that the client does not perceive the backend changes, and the master-slave seamless switch can be achieved. In the process of executing the actual storage business, the main server can activate its own HBA virtual port, and interact with the client for storage business based on its own HBA virtual port and binding relationship. The backup server needs to disable its own HBA virtual port and detect whether the main server is faulty. If it is determined that the main server is faulty, the backup server automatically upgrades to the main server, activates its own HBA virtual port, and interacts with the client for storage business based on its own HBA virtual port and binding relationship. In this way, dual-machine hot standby can be achieved only by the storage server, without the need to introduce an additional storage virtualization gateway, which can effectively reduce the deployment and operation and maintenance costs of the storage area network.

[0060] Based on the above embodiment, the storage service system provided by the embodiment of the present invention is introduced below. Figure 2 In the embodiment, the storage service system provided by the present invention includes a client 2, the storage system 1 as described above, and a FCSAN network, wherein the FCSAN network is arranged between the client 2 and the storage system 1, and the FCSAN network includes a fiber switch 3;

[0061] The fiber switch 3 is provided with a correspondence between the storage area network identifier of the HBA virtual port in the storage system and the storage area network identifier of the client 2, and is used to transfer storage service interaction data between the client and the HBA virtual port according to the correspondence.

[0062] It can be seen that in the storage service system provided by this embodiment, there is no need to set up a storage virtualization gateway. In addition, the fiber switch only needs to forward the storage service exchange data between the client and the storage system according to the correspondence between the storage area network identifier of the preset HBA virtual port and the storage area network identifier of the client. It can be seen that this embodiment can effectively simplify the structure of the storage service system, thereby improving the overall reliability of the system.

[0063] Based on the above embodiment, the storage processing method provided by this embodiment is introduced below. Figure 3 , Figure 3 A flowchart of a storage processing method provided by an embodiment of the present invention, the method is applied to any storage server in the storage system as described above, and the method may include:

[0064] S101. When determining that it is a master server, activate its own HBA virtual port, and perform storage service interaction with the client based on the binding relationship between its own HBA virtual port, the storage area network identifier of the HBA virtual port and the storage area network identifier of the client.

[0065] In this step, when the storage server determines that it is the primary server, it needs to activate its own HBA virtual port and interact with the client for storage services based on the binding relationship between its own HBA virtual port, the storage area network identifier of the HBA virtual port and the storage area network identifier of the client, that is, it needs to undertake storage services.

[0066] It should be noted that this embodiment does not limit how the primary server provides storage services for the client and how it interacts with the client for storage services. For example, the primary server can create a virtual unit (LUN) for the client and provide storage services for the client based on the virtual unit.

[0067] S102: When determining that it is a backup server, disabling its own HBA virtual port and detecting whether the main server is faulty; when determining that the main server is faulty, upgrading to the main server, activating its own HBA virtual port, and interacting with the client for storage services based on its own HBA virtual port and the binding relationship.

[0068] In this step, when the storage server determines that it is a standby server, it needs to keep its HBA virtual port disabled, that is, it does not interact with the client for storage services. In addition, the standby server also needs to detect whether the main server is faulty, and automatically upgrade to the main server when it determines that the main server is faulty, and start to take on storage services. In this way, automatic switching between the main and standby servers can be achieved.

[0069] It should be noted that this embodiment does not limit how the backup server detects whether the main server is faulty. For example, the backup server can query the device status of the main server through the network, and determine whether the main server is faulty based on the device status. For another example, the main server can actively output a heartbeat signal to the backup server, and the backup server can detect whether the main server is faulty based on the heartbeat signal. Since the heartbeat mechanism is highly reliable and is convenient for timely detection of main server faults, this embodiment will use the heartbeat mechanism to perform fault detection on the main server.

[0070] Based on this, the method may further include:

[0071] Step 11: When it is determined that it is the primary server, it periodically outputs a heartbeat signal;

[0072] The detecting whether the primary server fails may include:

[0073] Step 21: When determining that it is a backup server, detect whether the main server is faulty through the heartbeat signal sent by the main server.

[0074] It is worth pointing out that the heartbeat mechanism can be implemented based on the Keepalived service, where Keepalived is an open source software that provides high availability and load balancing solutions. It is mainly used to ensure high availability of services in a cluster environment and can distribute loads among multiple servers to improve system performance and stability.

[0075] Furthermore, if the storage servers form a DRDB cluster together and store the same user data synchronously based on the DRDB cluster, the primary server should be set as the host of the DRDB cluster, and the backup server should be set as the backup of the DRDB cluster. In addition, when performing a primary-backup switch, the backup server also needs to switch itself to the host of the DRDB cluster.

[0076] Based on this, the method may further include:

[0077] Step 31: When determining that it is the primary server, setting itself as the host of the DRDB cluster;

[0078] Step 32: When determining that it is a backup server, it sets itself as a backup server of the DRDB cluster; when upgrading to the primary server, it switches itself to the host of the DRDB cluster.

[0079] Furthermore, after the backup server is upgraded to the primary server, if the previously failed primary server recovers from the failed state to the normal state, in order to avoid conflicts, the previously failed primary server needs to disable its own HBA virtual port and automatically downgrade to a backup server.

[0080] Based on this, the method may further include:

[0081] Step 41: When determining that it is the main server, if it is determined that it has recovered from the fault state to the normal state, it disables its own HBA virtual port and downgrades to the standby server.

[0082] Furthermore, the HBA virtual port should be created based on the HBA physical card in the storage server. To ensure that each HBA virtual port has the same storage area network identifier, each storage server can create an HBA virtual port based on its own HBA physical card and a preset storage area network identifier. In addition, to ensure that the HBA virtual port can provide storage services to the client, each storage server also needs to create a storage area network server based on the HBA virtual port.

[0083] Based on this, the method may further include:

[0084] Step 51: Create the HBA virtual port based on its own HBA physical card and a preset storage area network identifier;

[0085] Step 52: Create a storage area network server based on the HBA virtual port.

[0086] Furthermore, when the storage servers form a cluster together, since only the host can bind the client, the master server can create a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client, and record the binding relationship in the configuration file. Subsequently, the master server can synchronize this configuration file to all standby servers, so that when the standby server is upgraded to the master server, the above binding relationship can be restored from the configuration file.

[0087] Based on this, the method may further include:

[0088] Step 61: when determining that the server itself is the master server, creating a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client, and recording the binding relationship in a configuration file;

[0089] Step 62: Synchronize the configuration file to all the standby servers.

[0090] Based on the above embodiment, the configuration process of the storage server and the fiber switch is introduced below based on a specific example. The configuration process of the storage server is as follows:

[0091] 1. Prepare two storage servers, two HBA cards and n SATA / SAS hard disks. Insert the two HBA cards into the two storage servers respectively and insert the hard disks into the storage server hard disk slots. After powering on, first check whether the HBA cards and hard disks are correctly identified.

[0092] 2. Build a DRBD cluster with two servers to synchronize block device data. The results of the master server show that the DRBD status is primary; the results of the slave server show that the DRBD status is secondary.

[0093] 3. Create the HBA card port server.

[0094] 4. Create a virtual port for the HBA card and use the virtual port to build the FCSAN server.

[0095] 6. Create drbd0 (the storage space formed by the drdb cluster) as a shared disk.

[0096] 7. Create a client under the virtual port of the HBA card.

[0097] 8. Create a logical unit under the virtual port of the HBA card and bind the client.

[0098] The backup server configures the virtual port in the same way as the primary server. Since the DRBD of the backup server does not allow operations, the backup server does not create a logical unit under normal conditions.

[0099] The configuration process of the fiber optic switch is as follows:

[0100] 1. Connect and log in to the fiber switch. First, connect to the fiber switch via SSH or serial port and log in using the administrator account.

[0101] 2. Create Zone Configuration:

[0102] On a fiber switch, you can set up zones using the CLI command or the web management interface. Zones can be configured based on WWN (World Wide Name) or physical ports. The following are the steps to create a zone using the CLI command.

[0103] 3. Create a new Zone:

[0104] Enter the zone configuration mode and create a zone for each device that needs to communicate. The zone name should be able to identify the corresponding HBA card and storage port.

[0105] Create a zone named "Server1_to_Storage1":

[0106] zonecreate "Server1_to_Storage1", "HBA_WWN;Storage_Port_WWN"

[0107] For example, if the WWN of the storage device HBA card is "2100f4c7aa0424aa" and the WWN of the client device port is "51402ec001c5485c", the command is as follows:

[0108] zonecreate "Server1_to_Storage1", "21:00:f4:c7:aa:04:24:aa;51:40:2e:c0:01:c5:48:5c"

[0109] 4. Create Zone Set:

[0110] Zone Set is the overall zone configuration of a fiber optic switch. Add the created zone to a Zone Set so that it can be applied to the Fabric (switching structure) of the switch.

[0111] 5. Activate Zone Set:

[0112] The Zone configuration takes effect only after the Zone Set is activated.

[0113] The client transmits data with the virtual port of the primary server. Set up a primary-backup switching script on the storage server to monitor the status of the primary storage server and control the activation of the virtual WWN. By default, the virtual port WWN of the primary server remains activated and the virtual port WWN of the backup server is disabled. When the primary server fails, the backup server automatically enables the virtual WWN and takes over the connection. You can deploy a primary-backup script on the backup server to monitor the status of the primary server and automatically enable the virtual WWN of the backup server when the primary server fails. When the primary server goes down, the backup server automatically becomes the primary server, immediately creates a logical unit, and binds the virtual port.

[0114] Based on the above embodiment, the storage processing method provided by this embodiment is introduced below. Figure 4 , Figure 4 This is a structural block diagram of a storage processing device provided by an embodiment of the present invention. The device is applied to any storage server in the storage system as described above, and may include:

[0115] The main server service module 401 is used to activate its own HBA virtual port when determining that it is the main server, and perform storage service interaction with the client based on the binding relationship between its own HBA virtual port, the storage area network identifier of the HBA virtual port and the storage area network identifier of the client;

[0116] The backup server business module 402 is used to disable its own HBA virtual port and detect whether the main server is faulty when it is determined to be a backup server; upgrade to the main server when it is determined that the main server is faulty, activate its own HBA virtual port, and interact with the client for storage business based on its own HBA virtual port and the binding relationship.

[0117] Optionally, the device may further include:

[0118] The master server downgrade module is used to disable its own HBA virtual port and downgrade to the standby server when it is determined that it is the master server and it is determined that it has recovered from the fault state to the normal state.

[0119] Optionally, the storage servers jointly form a DRDB cluster, and synchronously save the same user data based on the DRDB cluster; the device may further include:

[0120] A master server configuration module, used for setting itself as the host of the DRDB cluster when determining that it is the master server;

[0121] The standby server configuration module is used to set itself as a standby machine of the DRDB cluster when it is determined to be a standby server; when it is upgraded to the main server, it switches itself to the main machine of the DRDB cluster.

[0122] Optionally, the device may further include:

[0123] A configuration file creation module, for creating a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client when determining that the server itself is a master server, and recording the binding relationship in a configuration file;

[0124] A synchronization module is used to synchronize the configuration file to all the backup servers.

[0125] Optionally, the device may further include:

[0126] A heartbeat signal output module, used to periodically output a heartbeat signal when determining that it is the main server;

[0127] The fault detection module is used to detect whether the main server is faulty through the heartbeat signal sent by the main server when it is determined that the main server is a backup server.

[0128] Optionally, the device may further include:

[0129] A virtual port creation module, used for creating the HBA virtual port based on its own HBA physical card and a preset storage area network identifier;

[0130] The server creation module is used to create a storage area network server based on the HBA virtual port.

[0131] Please refer to Figure 5 , Figure 5This is a structural block diagram of a storage server provided in an embodiment of the present invention. The embodiment of the present invention provides a storage server 10, including a processor 11 and a memory 12; wherein the memory 12 is used to store computer programs; and the processor 11 is used to execute the storage processing method provided in the aforementioned embodiment when executing the computer program.

[0132] For the specific process of the above storage processing method, please refer to the corresponding content provided in the above embodiments, which will not be repeated here.

[0133] Furthermore, the memory 12 as a carrier for storing resources may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the storage method may be temporary storage or permanent storage.

[0134] In addition, the storage server 10 also includes a power supply 13, a communication interface 14, an input / output interface 15 and a communication bus 16; wherein the power supply 13 is used to provide working voltage for each hardware device on the storage server 10; the communication interface 14 can create a data transmission channel between the storage server 10 and external devices, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present invention, and is not specifically limited here. For example, the communication interface 14 can be an HBA interface or a network interface; the input / output interface 15 is used to obtain external input data or output data to the outside world. The specific interface type can be selected according to specific application needs and is not specifically limited here.

[0135] An embodiment of the present invention further provides a computer program product, including a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the storage processing method described in the above embodiment is implemented.

[0136] Since the embodiments of the computer program product part correspond to the embodiments of the storage processing method part, please refer to the description of the embodiments of the storage processing method part for the embodiments of the computer program product part, and will not be repeated here.

[0137] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the storage processing method described in the above embodiment is implemented.

[0138] Since the embodiments of the computer-readable storage medium part correspond to the embodiments of the storage processing method part, the embodiments of the storage medium part refer to the description of the embodiments of the storage processing method part, which will not be repeated here.

[0139] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0140] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0141] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0142] The storage system, storage service system, storage processing method and storage server provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the present invention.

Claims

1. A storage system, characterized in that: The storage system comprises at least two storage servers; the storage servers synchronously store the same user data, are provided with HBA virtual ports having the same storage area network identifier, and are provided with a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client; The storage server includes a backup server and a main server; The master server is used to activate its own HBA virtual port and perform storage service interaction with the client based on its own HBA virtual port and the binding relationship; The standby server is used to disable its own HBA virtual port and detect whether the main server fails; when it is determined that the main server fails, it is upgraded to the main server, activates its own HBA virtual port, and interacts with the client for storage services based on its own HBA virtual port and the binding relationship.

2. The storage system according to claim 1, characterized in that: The storage servers jointly form a DRDB cluster, and synchronously store the same user data based on the DRDB cluster.

3. A storage service system, characterized in that: include: A client, a storage system according to claim 1 or 2, and a FCSAN network, wherein the FCSAN network is arranged between the client and the storage system, and the FCSAN network includes a fiber optic switch; The fiber switch is provided with a correspondence between the storage area network identifier of the HBA virtual port in the storage system and the storage area network identifier of the client, and is used to transfer storage service interaction data between the client and the HBA virtual port according to the correspondence.

4. A storage processing method, characterized in that: Applied to any storage server in the storage system according to claim 1 or 2, the method comprises: When determining that it is the main server, activating its own HBA virtual port, and performing storage service interaction with the client based on the binding relationship between its own HBA virtual port, the storage area network identifier of the HBA virtual port and the storage area network identifier of the client; When it is determined that it is a backup server, it disables its own HBA virtual port and detects whether the main server is faulty; when it is determined that the main server is faulty, it is upgraded to the main server, activates its own HBA virtual port, and interacts with the client for storage services based on its own HBA virtual port and the binding relationship.

5. The storage processing method according to claim 4, characterized in that: Also includes: When it is determined that it is the main server, if it is determined that it has recovered from the fault state to the normal state, it will disable its own HBA virtual port and downgrade to the standby server.

6. The storage processing method according to claim 5, characterized in that: The storage servers jointly form a DRDB cluster, and synchronously store the same user data based on the DRDB cluster; The method further comprises: When determining that it is the primary server, it sets itself as the host of the DRDB cluster; When it is determined that it is a backup server, it sets itself as a backup machine of the DRDB cluster; when it is upgraded to the main server, it switches itself to the main machine of the DRDB cluster.

7. The storage processing method according to claim 4, characterized in that: Also includes: When determining that the server itself is a master server, creating a binding relationship between the storage area network identifier of the HBA virtual port and the storage area network identifier of the client, and recording the binding relationship in a configuration file; The configuration file is synchronized to all the standby servers.

8. The storage processing method according to claim 4, characterized in that: Also includes: When it determines itself as the primary server, it periodically outputs heartbeat signals; The detecting whether the main server fails comprises: When it is determined that the server is a standby server, it detects whether the main server is faulty through the heartbeat signal sent by the main server.

9. The storage processing method according to any one of claims 4 to 8, characterized in that: Also includes: Creating the HBA virtual port based on its own HBA physical card and a preset storage area network identifier; A storage area network server is created based on the HBA virtual port.

10. A storage processing device, characterized in that: Applied to any storage server in the storage system according to claim 1 or 2, the device comprises: The main server service module is used to activate its own HBA virtual port when determining that it is the main server, and perform storage service interaction with the client based on the binding relationship between its own HBA virtual port, the storage area network identifier of the HBA virtual port and the storage area network identifier of the client; The backup server business module is used to disable its own HBA virtual port and detect whether the main server is faulty when it is determined that it is a backup server; upgrade to the main server when it is determined that the main server is faulty, activate its own HBA virtual port, and interact with the client for storage business based on its own HBA virtual port and the binding relationship.

11. A storage server, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the storage processing method according to any one of claims 4 to 9 when executing the computer program.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are loaded and executed by the processor, the storage processing method according to any one of claims 4 to 9 is implemented.

Images