CN104461705A - Service access method, storage controllers and cluster storage system - Google Patents

Abstract

Embodiments of the present invention provide a service access method, a storage controller, and a cluster storage system, which relate to the field of computers and solve the problem that a main storage controller in an existing cluster storage system is prone to performance bottlenecks. The method includes: all storage controllers in the cluster storage system store the resource locks of all operation objects in the storage space of the cluster storage system, and when any storage controller receives an operation instruction of the host service, the The operation instruction includes an operation object identifier, and according to the operation object identifier, it is determined that the resource lock of the operation object stored by the first storage controller is in an unused state; the resource lock of the operation object is locked, and after locking The resource lock is in use; access the operation object according to the operation instruction. The embodiment of the present invention is used for service access.

Description

A service access method, storage controller, and cluster storage system

technical field

The invention relates to the computer field, in particular to a service access method, a storage controller, and a cluster storage system.

Background technique

In order to meet the continuous improvement of users' demand for storage, a "cluster storage system" is proposed in the prior art, which improves the capacity, reliability and availability of storage resources.

As shown in FIG. 1 , the cluster storage system proposed in the prior art is composed of multiple storage controllers, storage spaces and switches. Among them, the storage space can be composed of multiple independent disks, which are used to store data; the storage controller is used to read or write data in the storage space; the storage controller and the storage space are connected to the network through a switch, and any storage control The controller can access all operation objects in the storage space through this switch.

Since the same operation object in the storage space may be accessed multiple times at the same time, in order to ensure the uniqueness and certainty of the data in the storage space, resource locks are usually set for the operation object. Mutual exclusion between the services of the operation object. Specifically, when the operation object is accessed by a certain business, the resource lock corresponding to the operation object can be set to the used state, and other services are prohibited from accessing the operation object. This process is the locking process of the resource lock; After the business is executed, set the resource lock corresponding to the operation object to an unused state to allow other services to access the operation object. This process is the release process of the resource lock.

However, in an existing clustered storage system, a certain storage controller among multiple storage controllers is usually used as a primary storage controller, and other storage controllers are used as backup storage controllers. Each storage controller will apply to the main storage controller to lock or release the resource lock when performing business. In this way, when there are a large number of services concurrently sending applications to the main storage controller, the main storage controller will become The bottleneck of the entire cluster storage system.

Contents of the invention

The invention provides a service access method, a storage controller, and a cluster storage system to solve the problem that the main storage controller in the existing cluster storage system is prone to performance bottlenecks.

In order to achieve the above object, embodiments of the present invention adopt the following technical solutions:

In the first aspect, a method for service access is provided, the method is applied to a clustered storage system including at least two storage controllers, and the at least two storage controllers both store the data stored in the storage space of the clustered storage system Resource locks for all operation objects, the methods include:

The first storage controller receives an operation instruction of the host service; the operation instruction includes an operation object identifier; the first storage controller is any one of the at least two storage controllers;

determining according to the operation object identifier that the resource lock of the operation object stored by the first storage controller is in an unused state;

Locking the resource lock of the operation object, and the resource lock after locking is in a used state;

The operation object is accessed according to the operation instruction.

In a first possible implementation manner of the first aspect, the method further includes:

receiving an operation instruction of a background service, where the operation instruction of the background service includes the operation object identifier;

lock the resource lock of the operation object when it is determined that the resource lock of the operation object stored by the first storage controller is in an unused state;

Sending lock request messages to all storage controllers in the clustered storage system except the first storage controller respectively, where the lock request messages are used to instruct the storage controllers to lock the resource lock of the operation object Lock;

After all the storage controllers in the cluster storage system lock the resource locks of the operation object, they access the operation object according to the operation instruction of the background service.

With reference to the first aspect or the first possible implementation manner of the first aspect, in a second possible implementation manner, the method further includes:

receiving a lock request message including the operation object identifier sent by a second storage controller; the second storage controller is any storage controller in the cluster storage system except the first storage controller;

Lock the resource lock of the operation object stored by the first storage controller according to the lock request message;

Send a lock response message to the second storage controller.

With reference to the first aspect or the first possible implementation manner of the first aspect, in a third possible implementation manner, after accessing the operation object according to the operation instruction, include:

releasing the resource lock of the operation object stored by the first storage controller, and the released resource lock is in an unused state;

After accessing the operation object according to the operation instruction of the background business, it includes:

releasing the resource lock of the operation object stored by the first storage controller;

Sending a state change message to all storage controllers in the cluster storage system except the first storage controller, so that the storage controller receiving the state change message releases the resource lock of the operation object.

In a second aspect, a storage controller is provided, including:

The storage unit is used to store the resource locks of all operation objects in the storage space of the cluster storage system;

The first receiving unit is configured to receive an operation instruction of the host service, where the operation instruction includes an operation object identifier;

A locking unit, configured to determine, according to the operation object identifier, that the resource lock of the operation object stored by the storage controller is in an unused state, and lock the resource lock of the operation object; the locked The resource lock is in use;

A first access unit, configured to access the operation object according to the operation instruction.

In the first possible implementation manner of the second aspect, it also includes:

The second receiving unit is configured to receive an operation instruction of a background service, where the operation instruction of the background service includes the operation object identifier;

a sending unit, configured to send a lock request message to all storage controllers in the cluster storage system except the storage controller, and the lock request message is used to instruct the storage controller to use resources of the operation object Lock to lock;

The second access unit is configured to access the operation object according to the operation instruction of the background service after all the storage controllers in the cluster storage system have completed locking the resource locks of the operation object.

In combination with the second aspect or the first possible implementation of the second aspect, the second possible implementation also includes:

The third receiving unit is configured to receive the lock request message including the operation object identifier sent by the second storage controller; the second storage controller is any storage controller in the cluster storage system except the storage controller a storage controller;

The locking unit is further configured to lock the resource lock of the operation object stored by the storage controller according to the lock request message;

The sending unit is configured to send a lock response message to the second storage controller.

In combination with the second aspect or the first possible implementation manner of the second aspect, the third possible implementation manner further includes:

A releasing unit, configured to release the resource lock of the operation object stored by the storage controller after the first access unit accesses the operation object according to the operation instruction, and the released resource lock is not status of use;

After the second access unit accesses the operation object according to the operation instruction of the background service, release the resource lock of the operation object stored by the storage controller;

The sending unit is further configured to send a state change message to all storage controllers in the cluster storage system except the storage controller, so that the storage controller receiving the state change message will set the operation object to The resource lock is released.

In a third aspect, a cluster storage system is provided, including a storage space and at least two storage controllers, the at least two storage controllers are both connected to the storage space, and any of the at least two storage controllers The storage controller is respectively connected to all other storage controllers;

The storage controller is the storage controller described in any one of the possible implementation manners in the second aspect to the third possible implementation manner of the second aspect;

The storage space is used to store operation objects.

With the above scheme, when any storage controller in the cluster storage system receives an operation instruction from the host, it only needs to lock the resource lock of the corresponding operation object stored by the storage controller, and then access the server according to the operation instruction. The operation object does not need to send a lock request message to other storage controllers. Compared with the prior art, when the storage controller receives the operation command of the host service, it needs to send a lock request message to the main storage controller to request lock. The invention improves the execution efficiency of the host business, and because the locking status of each storage controller is equal, no performance bottleneck will occur in a certain storage controller.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For Those of ordinary skill in the art can also obtain other drawings based on these drawings without making creative efforts.

FIG. 1 is a schematic structural diagram of a cluster storage system in the prior art;

FIG. 2 is a schematic diagram of applying for locks between storage controllers in an existing cluster storage system;

FIG. 3 is a schematic flowchart of a service access method provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of applying for locking between storage controllers according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a storage controller provided by an embodiment of the present invention;

FIG. 6 is a schematic structural diagram of another storage controller provided by an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a clustered storage system provided by an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

In order to enable those skilled in the art to quickly understand the difference between the technical solution provided by the present invention and the prior art, terms related to the present invention will be described below, and existing service access methods will be introduced.

1) Background business: In order to maintain its own reliability, the cluster storage system spontaneously executes safeguard measures in the background, such as data backup, data migration, etc. Since the maintenance of the system does not require real-time operation, this background business has a low frequency of occurrence features.

2) Host business: The cluster storage system receives the data read and write operations executed by the instructions issued by the user. The host business is carried out in real time and has the characteristics of high occurrence frequency, and the cluster storage system host business will not be performed multiple times at the same time access the same operand.

3) Operation object: the address used to store data in the storage space.

4) Resource lock: the only "key" required by the storage controller to access the operation object. The storage controller can only access the operation object when it determines that the resource lock corresponding to the operation object to be accessed is in an unused state.

The existing cluster storage system is shown in Figure 2, the cluster storage system includes: a main storage controller, at least one backup storage controller, and a storage space, wherein the main storage controller is connected to each backup storage controller, All storage controllers (including primary storage controller and backup storage controller) are respectively connected to the storage space; all storage controllers are used to access operation objects in the storage space; the primary storage controller is also used to manage the storage space The resource lock corresponding to each operation object in . It can be seen from Figure 2 that each storage controller will apply to the main storage controller to lock the resource lock no matter whether it is executing host business or background business. Due to the high frequency of the host business, a large number of business operations are likely High concurrency applications to the primary storage controller cause performance bottlenecks in the primary storage controller.

An embodiment of the present invention provides a method for service access, which is applied to a clustered storage system. The clustered storage system includes at least two storage controllers, and each of the at least two storage controllers stores the data stored in the storage space of the clustered storage system. Resource locks for all operation objects, as shown in Figure 3, this method includes:

S301. The first storage controller receives an operation instruction of a host service; the operation instruction includes an operation object identifier.

Wherein, the first storage controller is any one of the at least two storage controllers.

S302. The first storage controller determines according to the operation object identifier that the resource lock of the operation object stored by the first storage controller is in an unused state.

S303. The first storage controller locks the resource lock of the operation object, and the locked resource lock is in a used state.

S304. The first storage controller accesses the operation object according to the operation instruction.

Exemplarily, steps S302 and S303 include: the first storage controller queries the use status of the resource lock corresponding to the operation object identifier in the lock configuration table stored by the first storage controller, wherein the lock configuration table includes the operation object identifier, and The operation object identifier corresponds to the usage state of the resource lock; if the resource lock is currently in the unused state, change the unused state of the resource lock to the used state; if the resource lock is currently in the used state, then After querying that the resource lock is in the unused state, change the unused state to the used state.

Wherein, the lock configuration table may be stored in the first storage controller in the form of a table, as shown in Table 1 below:

Table 1

Operand ID The state of the resource lock Operation object 1 Resource lock 1 is not used Operation object 2 Resource lock 2 is used ... ... Operation object N Resource lock 3 is not used

From Table 1, if the operation object is identified as operation object 1, then the first storage controller queries the state of the resource lock 1 corresponding to the operation object 1 in Table 1, and if the state of the resource lock 1 is unused, then The first storage controller changes the state of the resource lock 1 to a used state, and accesses the operation object 1 according to the operation instruction of the host service, and executes the host service; if the state of the resource lock 1 is in use, Then the first storage controller waits for the business currently occupying the resource lock 1 (the business is the background business of the first storage controller or the background business of other storage controllers) to finish executing, and changes the state of the resource lock 1 After it is in the unused state, change the state of the resource lock 1 to the used state.

The above Table 1 is just an example, and the lock configuration table can also be stored in the first storage controller in other forms, and the specific form can be determined according to actual needs, which is not limited in the present invention.

Using the above method, when any storage controller in the cluster storage system receives an operation command of the host service, it only needs to lock the resource lock of the corresponding operation object stored by the storage controller, and can access the server according to the operation command. The operation object does not need to send a lock request message to other storage controllers. Compared with the prior art, when the storage controller receives the operation command of the host service, it needs to send a lock request message to the main storage controller to request lock. The invention improves the execution efficiency of the host business, and because the locking status of each storage controller is equal, no performance bottleneck will occur in a certain storage controller.

However, in order to ensure that the first storage controller only needs to lock the resource lock of the corresponding operation object stored by the first storage controller when executing the host service, it can be mutually exclusive with other services, in the embodiment of the present invention In a possible implementation manner of , any storage controller in the clustered storage system needs to request locks from all storage controllers in the clustered storage system before executing background services.

Specifically, the first storage controller receives an operation instruction of the background service, and the operation instruction of the background service includes the operation object identifier; when it is determined that the resource lock of the operation object stored by the first storage controller is in an unused state, Lock the resource lock of the operation object; send a lock request message to all storage controllers in the cluster storage system except the first storage controller respectively, and the lock request message is used to instruct the storage controller to the The resource lock of the operation object is locked; after all the storage controllers in the cluster storage system complete the locking of the resource lock of the operation object, they access the operation object according to the operation instruction of the background business.

For example, the lock request message carries the operation object identifier, and after receiving the lock request message, the second storage controller locks the resource lock of the operation object stored in the second storage controller according to the operation object identifier. Locking is performed, and after the locking is successful, a lock response message is sent to the first storage controller. The process of locking the resource lock by the second storage controller can refer to the above-mentioned operation object identifier of the first storage controller. The process of locking the corresponding resource lock will not be repeated here.

Further, the first storage controller executes the background service after all storage controllers in the cluster storage system are successfully locked, that is, the first storage controller performs the background service on its own storage corresponding to the operation object identifier After the resource lock is successfully locked and the lock response messages sent by all storage controllers in the cluster storage system except the first storage controller are received, the background service is executed.

Exemplarily, each storage controller in the cluster storage system stores the lock configuration table shown in Table 1 above. As shown in Figure 4, the first storage controller sends a lock application message to the second storage controller, and the lock application message includes the identifier of the operation object 1, then the second storage controller receives the lock application After receiving the message, query the lock configuration table stored by the second storage controller. If the status of the resource lock 1 corresponding to the operation object 1 in the lock configuration table stored by the second storage controller is unused, the second storage The controller changes the status of the resource lock 1 to the used status, and sends a lock response message to the first storage controller, indicating that the first storage controller is successfully locked. If the resource lock 1 corresponding to the operation object 1 is in the used state, wait for the service currently occupying the resource lock 1 to be executed and release the resource lock 1, and then determine that the resource lock 1 is in the unused state, then the second The second storage controller changes the status of the resource lock 1 to the used status, and sends a lock response message to the first storage controller, indicating that the first storage controller has successfully locked it.

In addition, when the first storage controller receives the lock request message including the operation object identifier sent by the second storage controller, the resources of the operation object stored in the first storage controller according to the lock request message The lock is locked, and after the lock is completed, a lock response message is sent to the second storage controller, and the second storage controller is any storage controller in the cluster storage system except the first storage controller .

In this way, when the first storage controller is executing the background business, the resource locks corresponding to the operation objects of the background business in the lock configuration table stored by each storage controller in the cluster storage system are in the used state. , each storage controller in the cluster storage system cannot perform other services for the operation object, which ensures mutual exclusion among services.

In addition, when the second storage controller executes the background service, the first storage controller will also receive the lock request message sent by the second storage controller and perform locking. In this way, when any storage controller of the cluster storage system executes a background service on the operation object, the resource locks corresponding to the operation object of all storage controllers in the cluster storage system are in a used state. That is to say, if the resource lock corresponding to the operation object stored by a certain storage controller is in an unused state, it indicates that there is no storage controller performing background business on the operation object at this time. At this time, if the storage controller After receiving the operation instruction to execute the host business on the operation object, the host business can be executed only by locking the resource lock corresponding to the operation object stored by itself (because the host business of the cluster storage system is not much at the same time). Access to the same operation object at a time, so there is no need to consider the mutual exclusion between different host services).

Further, the first storage controller needs to release the resource lock occupied by the service after executing the service. Specifically, after the first storage controller accesses the operation object according to the operation instruction of the host service, the resource lock of the operation object stored in the first storage controller is released, and the resource lock after release is in an unused state ; After the first storage controller accesses the operation object according to the operation instruction of the background service, the resource lock of the operation object stored by the first storage controller is released, and the cluster storage system except the first All storage controllers other than the storage controller send a state change message, so that the storage controller that receives the state change message releases the resource lock of the operation object.

It can be seen from the above that the storage controller in the embodiment of the present invention does not apply for locks from other storage controllers when executing the host business, which will not cause a performance bottleneck of a storage controller. At the same time, in addition, because the cluster storage system Each storage controller in the cluster stores the corresponding relationship between the operation object identifier and the usage status of the resource lock. Therefore, if a storage controller fails, it will not affect the service access of the cluster storage system.

An embodiment of the present invention provides a storage controller 50, which corresponds to the method embodiment in FIG. 3 above, and each functional unit of the storage controller 50 can be used in the above method steps. As shown in Figure 5, the storage controller 50 includes:

The storage unit 51 is configured to store resource locks of all operation objects in the storage space of the cluster storage system.

The first receiving unit 52 is configured to receive an operation instruction of the host service, where the operation instruction includes an operation object identifier.

The locking unit 53 is configured to determine, according to the operation object identifier, that the resource lock of the operation object stored by the storage controller is in an unused state, and lock the resource lock of the operation object; the locked resource lock is used status of use.

The first access unit 54 is configured to access the operation object according to the operation instruction.

Using the above method, when any storage controller in the cluster storage system receives an operation command of the host service, it only needs to lock the resource lock of the corresponding operation object stored by the storage controller, and can access the server according to the operation command. The operation object does not need to send a lock request message to other storage controllers. Compared with the prior art, when the storage controller receives the operation command of the host service, it needs to send a lock request message to the main storage controller to request lock. The invention improves the execution efficiency of the host business, and because the locking status of each storage controller is equal, no performance bottleneck will occur in a certain storage controller.

However, in order to ensure that the storage controller only needs to lock the resource lock of the corresponding operation object stored by the storage controller when executing the host service, it can be mutually exclusive with other services. In an implementation manner, any storage controller in the cluster storage system needs to request locks from all storage controllers in the cluster storage system before executing background services.

Therefore, optionally, the storage controller also includes:

The second receiving unit 55 is configured to receive an operation instruction of a background service, where the operation instruction of the background service includes the operation object identifier.

The sending unit 56 is configured to send a lock request message to all storage controllers in the cluster storage system except the storage controller, and the lock request message is used to instruct the storage controller to lock the resource lock of the operation object. Lock.

The second access unit 57 is configured to access the operation object according to the operation instruction of the background service after all the storage controllers in the cluster storage system finish locking the resource locks of the operation object.

For example, the lock request message carries the operation object identifier, and after receiving the lock request message, the second storage controller locks the resource lock of the operation object stored in the second storage controller according to the operation object identifier. Locking is performed, and after the locking is successful, a locking response message is sent to the storage controller.

Further, the storage controller executes the background business after all storage controllers in the cluster storage system are successfully locked, that is, the storage controller locks the resource lock corresponding to the operation object identifier stored in itself After the process is successful, and the lock response messages sent by all the storage controllers in the cluster storage system except the storage controller are received, the background service is executed.

Optionally, the storage controller also includes:

The third receiving unit 58 is configured to receive the lock request message including the operation object identifier sent by the second storage controller; the second storage controller is any storage controller in the cluster storage system except the storage controller device.

The locking unit 53 is further configured to lock the resource lock of the operation object stored by the storage controller according to the lock request message.

The sending unit 56 is configured to send a lock response message to the second storage controller.

In this way, when the storage controller is executing the background business, the status of the resource lock corresponding to the operation object of the background business in the lock configuration table stored by each storage controller in the cluster storage system is in the used state. Each storage controller in the cluster storage system cannot perform other services for the operation object, which ensures mutual exclusion among services.

In addition, when the second storage controller executes the background service, the storage controller will also receive the lock request message sent by the second storage controller and perform locking. In this way, when any storage controller of the cluster storage system executes a background service on the operation object, the resource locks of all storage controllers in the cluster storage system corresponding to the operation object are in a used state. That is to say, if the resource lock corresponding to the operation object stored by a certain storage controller is in an unused state, it indicates that there is no storage controller performing background business on the operation object at this time. At this time, if the storage controller After receiving an operation instruction to execute the host business on the operation object, the host business can be executed only by locking the resource lock corresponding to the operation object stored by itself (because the cluster storage system does not have many host businesses at the same time). Access to the same operation object at a time, so there is no need to consider the mutual exclusion between different host services).

Further, the storage controller needs to release the resource lock occupied by the service after executing the service. Therefore, optionally, the storage controller also includes:

The release unit 59 is configured to release the resource lock of the operation object stored in the storage controller after the first access unit accesses the operation object according to the operation instruction, and the released resource lock is in an unused state; After the second access unit accesses the operation object according to the operation instruction of the background business, the resource lock of the operation object stored in the storage controller is released; the sending unit 56 is also used to delete the storage in the cluster storage system All storage controllers other than the controller send a state change message, so that the storage controller that receives the state change message releases the resource lock of the operation object.

In addition, those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional modules according to needs. , that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. For the specific working process of the above-described system, device, and unit, reference may be made to the corresponding process in the foregoing method embodiments, and details are not repeated here.

The embodiment of the present invention provides a storage controller 60, the storage controller 60 is any storage controller in the cluster storage system, as shown in FIG. 6, including:

Processor (processor) 61, communication interface (Communications Interface) 62, memory (memory) 63 and communication bus 64; Wherein, described processor 61, described communication interface 62 and described memory 63 complete by described communication bus 64 mutual communication.

The processor 61 may be a multi-core CPU, or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention.

The memory 63 is used to store program codes and resource locks of operation objects, and the program codes include computer operation instructions and network flow diagrams. The memory 63 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.

The communication interface 62 is used to realize connection and communication between these devices.

The processor 61 is used to execute the program codes in the memory 63 to achieve the following operations:

The method is applied to a clustered storage system including at least two storage controllers, and each of the at least two storage controllers stores resource locks of all operation objects in the storage space of the clustered storage system, and the method includes:

receiving an operation instruction of a host service; the operation instruction includes an operation object identifier; the storage controller is any one of the at least two storage controllers;

determining according to the operation object identifier that the resource lock of the operation object stored by the storage controller is in an unused state;

Locking the resource lock of the operation object, and the resource lock after locking is in a used state;

The operation object is accessed according to the operation instruction.

Optionally, the operations also include:

receiving an operation instruction of a background service, where the operation instruction of the background service includes the operation object identifier;

Locking the resource lock of the operation object when it is determined that the resource lock of the operation object stored by the storage controller is in an unused state;

Sending lock request messages to all storage controllers in the cluster storage system except the storage controller respectively, where the lock request messages are used to instruct the storage controllers to lock the resource lock of the operation object;

After all the storage controllers in the cluster storage system lock the resource locks of the operation object, they access the operation object according to the operation instruction of the background service.

Optionally, the operations also include:

receiving a lock request message including the operation object identifier sent by a second storage controller; the second storage controller is any storage controller in the cluster storage system except the storage controller;

Lock the resource lock of the operation object stored by the storage controller according to the lock request message;

Send a lock response message to the second storage controller.

Optionally, after accessing the operation object according to the operation instruction, the operation further includes:

releasing the resource lock of the operation object stored by the storage controller, and the released resource lock is in an unused state;

After accessing the operation object according to the operation instruction of the background service, the operation further includes:

releasing the resource lock of the operation object stored by the storage controller;

Sending a state change message to all storage controllers in the cluster storage system except the storage controller, so that the storage controller receiving the state change message releases the resource lock of the operation object.

An embodiment of the present invention provides a cluster storage system 70, as shown in FIG. 7 , including:

A storage space 71 , a storage controller 72 and a storage controller 73 , wherein the storage space 71 is connected to the storage controller 72 and the storage controller 73 respectively, and the storage controller 72 is connected to the storage controller 73 .

The storage space 71 is used to store operation objects.

The storage controller 72 is the storage controller 50 or the storage controller 60 shown in FIG. 5 or FIG. 6, and the storage controller 73 is the storage controller 50 or the storage controller 60 shown in FIG. 5 or FIG. Refer to the description corresponding to FIG. 5 or FIG. 6 , which will not be repeated here.

With the above cluster storage system, when any storage controller in the cluster storage system receives an operation command of the host service, it only needs to lock the resource lock of the corresponding operation object stored by the storage controller, and the The operation instruction accesses the operation object without sending a lock request message to other storage controllers. Compared with the prior art, when the storage controller receives the operation instruction of the host service, it needs to send a lock request message to the main storage controller to request Locking, the present invention improves the execution efficiency of host business, and because the locking status of each storage controller is equal, it will not cause a performance bottleneck of a certain storage controller.

In the several embodiments provided in this application, it should be understood that the disclosed devices and methods may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

Those of ordinary skill in the art can understand that all or part of the steps for realizing the above-mentioned method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the It includes the steps of the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. All should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims (9)

1. A method for service access, characterized in that the method is applied to a clustered storage system comprising at least two storage controllers, and the at least two storage controllers are all stored in the storage space of the clustered storage system Resource locks for all operation objects, the methods include: The first storage controller receives an operation instruction of the host service; the operation instruction includes an operation object identifier; the first storage controller is any one of the at least two storage controllers; determining according to the operation object identifier that the resource lock of the operation object stored by the first storage controller is in an unused state; Locking the resource lock of the operation object, and the resource lock after locking is in a used state; The operation object is accessed according to the operation instruction. 2. The method according to claim 1, characterized in that the method further comprises: receiving an operation instruction of a background service, where the operation instruction of the background service includes the operation object identifier; lock the resource lock of the operation object when it is determined that the resource lock of the operation object stored by the first storage controller is in an unused state; Sending lock request messages to all storage controllers in the clustered storage system except the first storage controller respectively, where the lock request messages are used to instruct the storage controllers to lock the resource lock of the operation object Lock; After all the storage controllers in the cluster storage system lock the resource locks of the operation object, they access the operation object according to the operation instruction of the background service. 3. The method according to claim 1 or 2, characterized in that the method further comprises: receiving a lock request message including the operation object identifier sent by a second storage controller; the second storage controller is any storage controller in the cluster storage system except the first storage controller; Lock the resource lock of the operation object stored by the first storage controller according to the lock request message; Send a lock response message to the second storage controller. 4. The method according to claim 1 or 2, characterized in that, after accessing the operation object according to the operation instruction, comprising: releasing the resource lock of the operation object stored by the first storage controller, and the released resource lock is in an unused state; After accessing the operation object according to the operation instruction of the background business, it includes: releasing the resource lock of the operation object stored by the first storage controller; Sending a state change message to all storage controllers in the cluster storage system except the first storage controller, so that the storage controller receiving the state change message releases the resource lock of the operation object. 5. A storage controller, characterized in that, comprising: The storage unit is used to store the resource locks of all operation objects in the storage space of the cluster storage system; The first receiving unit is configured to receive an operation instruction of the host service, where the operation instruction includes an operation object identifier; A locking unit, configured to determine, according to the operation object identifier, that the resource lock of the operation object stored by the storage controller is in an unused state, and lock the resource lock of the operation object; the locked The resource lock is in use; A first access unit, configured to access the operation object according to the operation instruction. 6. The storage controller according to claim 5, further comprising: The second receiving unit is configured to receive an operation instruction of a background service, where the operation instruction of the background service includes the operation object identifier; a sending unit, configured to send a lock request message to all storage controllers in the cluster storage system except the storage controller, and the lock request message is used to instruct the storage controller to use resources of the operation object Lock to lock; The second access unit is configured to access the operation object according to the operation instruction of the background service after all the storage controllers in the cluster storage system have completed locking the resource locks of the operation object. 7. The storage controller according to claim 5 or 6, further comprising: The third receiving unit is configured to receive the lock request message including the operation object identifier sent by the second storage controller; the second storage controller is any storage controller in the cluster storage system except the storage controller a storage controller; The locking unit is further configured to lock the resource lock of the operation object stored by the storage controller according to the lock request message; The sending unit is configured to send a lock response message to the second storage controller. 8. The storage controller according to claim 5 or 6, further comprising: A releasing unit, configured to release the resource lock of the operation object stored by the storage controller after the first access unit accesses the operation object according to the operation instruction, and the released resource lock is not status of use; After the second access unit accesses the operation object according to the operation instruction of the background service, release the resource lock of the operation object stored by the storage controller; The sending unit is further configured to send a state change message to all storage controllers in the cluster storage system except the storage controller, so that the storage controller receiving the state change message will set the operation object to The resource lock is released. 9. A cluster storage system, characterized in that it comprises a storage space and at least two storage controllers, the at least two storage controllers are all connected to the storage space, and any of the at least two storage controllers A storage controller is respectively connected with all other storage controllers; The storage controller is the storage controller according to any one of claims 5 to 8; The storage space is used to store operation objects.