CN113626263A

CN113626263A - Method for keeping data consistency in SCST storage system and application

Info

Publication number: CN113626263A
Application number: CN202110920761.9A
Authority: CN
Inventors: 申江伟; 陈铎; 方敏
Original assignee: Anchao Cloud Software Co Ltd
Current assignee: Anchao Cloud Software Co Ltd
Priority date: 2021-08-11
Filing date: 2021-08-11
Publication date: 2021-11-09

Abstract

The invention discloses a method for keeping data consistency in an SCST storage system and application thereof, wherein the method comprises the following steps: after the current node logs in, whether the system has abnormity or other nodes are logged in is inquired through the zookeeper; if yes, the current node suspends I/O to clear the pending I/O for other nodes to perform I/O. According to the method for keeping the data consistency in the SCST storage system, the fact that the system is abnormal can be inquired according to the zookeeper, the suspended I/O operation is triggered and cleared, the phenomenon that the brain is split and the data is inconsistent due to the fact that other nodes are accessed subsequently is avoided, and the data consistency is guaranteed.

Description

Method for keeping data consistency in SCST storage system and application

Technical Field

The present invention relates to the field of computers, and more particularly, to a method and application for maintaining data consistency in an SCST storage system.

Background

With the rapid development and progress of computer technology, the data growth speed is continuously increased, and when a certain node fails due to hardware and software, another node can automatically and rapidly provide services to the outside. With the development of network storage technology, network storage is increasingly put into use, which provides a relatively strong support for service continuity and data availability.

The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

Disclosure of Invention

The invention aims to provide a method and application for maintaining data consistency in an SCST storage system, which can inquire whether the system is abnormal according to zookeeper, trigger and clear suspended I/O operation, ensure that the phenomenon of inconsistent data due to split brain cannot occur during subsequent access of other nodes and ensure the data consistency.

To achieve the above object, an embodiment of the present invention provides a method for maintaining data consistency in an SCST storage system.

In one or more embodiments of the invention, after a current node logs in, whether an abnormal node or other nodes log in the system exists is inquired through a zookeeper; if yes, the current node suspends I/O to clear pending I/O for other nodes to perform I/O.

In one or more embodiments of the present invention, the current node determines whether an abort I/O duration is greater than a set duration; and if so, restarting the SCST service by the current node or executing node restarting.

In one or more embodiments of the invention, the current node detects whether I/O information of other nodes exists in the zookeeper when logging in; and if so, the current node executes disconnection.

In one or more embodiments of the invention, the current node adds a valid tag to all node I/Os through zookeeper at login time, and notifies shared storage to update the valid tag so as to complete login.

In another aspect of the invention, a method for maintaining data consistency in an SCST storage system is provided.

In one or more embodiments of the invention, a shared storage receives an I/O write request of a current login node; and the shared storage adds an effective label to the I/O write request and writes the effective label into the I/O of the current login node.

In one or more embodiments of the invention, I/Os that do not update tags are discarded after the shared store adds a valid tag to the I/O write request.

In another aspect of the present invention, an apparatus for maintaining data consistency in an SCST storage system is provided, which includes a determining module and an executing module.

The judging module is used for inquiring whether the system has abnormity or other node logins through the zookeeper after the current node logins.

The execution module is used for the current node to suspend I/O so as to clear the suspended I/O, and other nodes can execute I/O.

In one or more embodiments of the present invention, the determining module is further configured to determine, by the current node, whether an abort I/O duration is greater than a set duration; and if so, restarting the SCST service by the current node or executing node restarting.

In one or more embodiments of the present invention, the determining module is further configured to detect whether there is I/O information of another node in the zookeeper when the current node logs in; and if so, the current node executes disconnection.

In one or more embodiments of the present invention, the execution module is further configured to add a valid tag to all node I/os by zookeeper when the current node logs in, and notify the shared storage to update the valid tag, so as to complete the login.

In another aspect of the present invention, an apparatus for maintaining data consistency in an SCST storage system is provided, which includes a storage module and a write module.

The storage module is used for receiving the I/O write request of the current login node by the shared storage.

And the write-in module is used for adding label information to the I/O write-in request by the shared storage and writing the label information into the I/O of the current login node.

In one or more embodiments of the present invention, the storage module is further configured to discard I/os with no updated tag after the shared storage adds a valid tag to the I/O write request.

In another aspect of the present invention, there is provided an electronic device including: at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform a method of maintaining data consistency in an SCST storage system as described above.

In another aspect of the present invention, a computer readable storage medium is provided, having stored thereon a computer program, which when executed by a processor, implements the steps of the method of maintaining data consistency in an SCST storage system as described.

Compared with the prior art, the method and the application for maintaining the data consistency in the SCST storage system can actively inquire whether the system is abnormal through the zookeeper, timely clear the I/O of the current node, ensure that all abnormal I/O is cleared within the specified time, and avoid resource contention caused by writing the I/O of a plurality of nodes into the shared storage. The time for clearing the I/O can be shortened by setting the shared storage, the I/O controllability is ensured, and the data consistency of the system is further ensured.

Drawings

FIG. 1 is a schematic diagram of a method for maintaining data consistency in an SCST storage system according to an embodiment of the invention;

FIG. 2 is a block diagram of a method for maintaining data consistency in an SCST storage system according to an embodiment of the invention;

FIG. 3 is a system diagram of a method for maintaining data consistency in an SCST storage system according to an embodiment of the invention;

FIG. 4 is an expanded flow diagram of a method for maintaining data consistency in an SCST storage system according to an embodiment of the invention;

FIG. 5 is a node structure diagram of a method for maintaining data consistency in an SCST storage system according to an embodiment of the invention;

FIG. 6 is a timing diagram of a method for maintaining data coherency in an SCST storage system according to an embodiment of the invention;

FIG. 7 is a modified flow diagram of a method for maintaining data consistency in an SCST storage system according to an embodiment of the invention;

FIG. 8 is a block diagram of an apparatus for maintaining data consistency in an SCST storage system according to an embodiment of the invention;

FIG. 9 is a hardware block diagram of a computing device for maintaining data consistency in an SCST storage system according to an embodiment of the invention.

Detailed Description

The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.

Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.

A typical SCST storage system is generally made up of 4 parts, namely client, VIP, SCST and shared storage.

The client is a client component of the iSCSI interface and mainly accesses the whole system resource through the process.

The VIP selects which node's resources to use for the client, and when the selected node fails, the VIP provides another node for the client connection to use.

The SCST is a common SCSI target subsystem of the Linux system, provides a unified interface for processing between Linux kernels and a SCSI target driver, and simultaneously provides a handle connection between the Linux kernels and a storage back end to connect a real or simulated storage back end and the target driver.

The shared storage is used for storing all I/O requests sent by the client and finally falls into a set of shared storage through different nodes.

Under normal conditions, a user sends a service request, a client requests a VIP, the VIP provides a proper node to the client through a resource selection function, the client executes read-write data operation, and an SCST module in the node receives the request and provides the request to a bottom layer of shared storage. When the network is disconnected or the node is abnormal, the VIP selects other nodes to provide to the client.

The technical solutions provided by the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

Example 1

Referring to fig. 1-2, a method for maintaining data consistency in an SCST storage system according to an embodiment of the present invention is described, which includes the following steps.

In step S101, the zookeeper queries whether there is an exception or other node login in the system.

zookeeper is a distributed application program coordination service, which is software that provides a consistent service for distributed applications, and provides functions including: configuration maintenance, domain name service, distributed synchronization, group service, etc. The zookeeper aims to package complex and error-prone key services and provide a simple and easy-to-use interface and a system with high performance and stable functions for a user.

Under normal conditions, a client requests a VIP, the VIP provides an appropriate node to the client through a resource selection function, the client performs read-write data operation, and an SCST module in the node receives the request and provides the request to a shared memory.

For example, the client selects the node 1 to perform login operation through the VIP, the node 1 is marked as login by the zookeeper, and the I/O is suspended, so that the I/O of the node 1 is prevented from passing through, and the problem that the shared storage cannot timely clear the I/O of the abnormal node when the node is abnormal is avoided. The zookeeper respectively checks the state of the node 1 and the state of the shared storage, and if the state of the node 1 or the state of the shared storage is abnormal, the node 1 cannot meet the connection requirement of the client and the system is abnormal. If the zookeeper inquires that other nodes are marked as login, it is indicated that the I/O of other nodes exists in the shared storage, and at this time, the I/O request of the node 1 is continuously executed, which may cause the nodes to contend for resources in the shared storage, generate split brain, and cause data inconsistency.

In step S102, the current node aborts the I/O to clear pending I/O for other nodes to perform I/O.

When the network is disconnected or the current node is abnormal, the VIP selects other nodes to provide for the client, and the other nodes replace the current node to execute data reading and writing operations.

For example, when node 1 is abnormal or the system is abnormal, node 1 suspends I/O to clear the hanging I/O, node 2 without abnormality is selected by VIP to be provided to the client, node 2 is logged by the client to execute the I/O request sent by the client, and the I/O is written into the shared storage.

In such an embodiment, the possibility that when the VIP selects other nodes for the client to use, the suspended I/O on the previous node continues to be written into the underlying shared storage, thereby contending with the shared resources of other nodes and causing split brain can be avoided.

Example 2

Referring to fig. 3 to 4, a method for maintaining data consistency in an SCST storage system according to another embodiment of the present invention is described, which includes the following steps.

In step S201, it is detected whether I/O information of another node exists in the zookeeper.

The I/O information of other nodes comprises that I/O of other nodes is allowed and the I/O which is not suspended exists, the zookeeper inquires that the I/O of other nodes is allowed, namely the VIP selects other nodes to provide to a client besides the current node, and the client performs login operation to other nodes and sends the I/O to the shared storage. And the zookeeper inquires that the I/O which is not suspended exists, namely the I/O which is not suspended by other nodes is not cleared in time when other nodes are in failure, and the I/O which is not suspended by other nodes still exists in the shared storage.

In step S202, the current node performs disconnection.

When the zookeeper detects the I/O information of other nodes, the current node does not continue to execute login operation any more, and the connection is disconnected. At this time, if the current node continues to connect and execute the login operation, the system fails, I/O of other nodes needs to be cleared first, then the connection of the current node is established, and the service sent by the client is executed.

In step S203, the zookeeper queries whether there is an exception or other node login in the system.

In step S204, the current node aborts the I/O to clear pending I/O for other nodes to perform I/O.

In step S205, the current node determines whether the I/O suspension duration is greater than a set duration.

In some specific scenarios, the service requirement cannot be met due to too long time for terminating the I/O, for example, when an Oracle service requires a system to fail, the fast switching can be performed, and the current node failure switching time can reach 60s, which obviously cannot meet the service, and the I/O termination needs to be accelerated by other means. In addition, I/O can not be controlled after reaching the shared storage, and the time for stopping I/O is prolonged.

In step S206, the current node restarts the SCST service or performs a node restart.

The I/O of the current node can be quickly suspended by restarting the SCST service of the current node or executing the node restart, and the I/O suspension time length and the service fault switching time length are shortened.

Taking fig. 3 as an example, when the node 1 is abnormal, the node 1 may actively determine its own abnormal condition through the zookeeper, thereby performing an operation of clearing all the suspended I/O, and after the clearing is successful, the information in the zookeeper may be updated, the I/O of the current node surface itself has been cleared, and when the suspension I/O is overtime, the SCST service is restarted or the node is restarted, so as to ensure that the suspended I/O is cleared. And the VIP reselects the node 2 for the client to log in, and the node 2 selected to process the I/O accesses the zookeeper to ensure that the I/O operation requested by the client is executed after the I/O clearing of the node 1 is completed or the specified time is exceeded.

The zookeeper can help the abnormal node to actively judge the state of the abnormal node to trigger the I/O clearing operation, all suspended I/O of the abnormal node is cleared within the specified time, the I/O of the abnormal node is controllable, and the data consistency of the system can be guaranteed.

Example 3

Referring to fig. 5 to 7, a method for maintaining data consistency in an SCST storage system according to another embodiment of the present invention is described, which includes the following steps.

In step S301, zookeeper adds a valid label to all node I/os and notifies shared storage to update the valid label.

Since shared storage only provides storage services via the Posix standard, it is not possible to add maintainable tag information across the VFS layer in an SCST storage system. However, since I/O existing in the SCST storage system can be managed and suspended efficiently, it is only necessary to solve the problem that I/O cannot be controlled after reaching the shared storage.

The VFS, called virtual file system or virtual file system translation, is a kernel software layer, an abstract layer above a concrete file system, for handling all calls related to the Posix file system, and is shown to provide a common interface for various file systems, so that applications on the upper layer can access different file systems using the common interface, and also provide a medium for communication of different file systems.

In this embodiment, after the current node is selected by the VIP for login, an I/O connection is normally established, and login information and tag information in the zookeeper are updated, and the zookeeper adds an effective tag to all node I/os. The tag information can be added when the I/O is written into the VFS layer, and the I/O is maintained by updating the effective tag information in the shared storage, so that the time for stopping the I/O and the time for switching the service failure can be greatly shortened.

In step S302, the shared storage receives an I/O write request of the current login node, adds a valid tag to the I/O write request, and writes the I/O of the current login node.

After the zookeeper inquires whether the system is abnormal or other nodes are logged in, the client executes write operation, the client sends an I/O write request to the current login node, the current login node sends the I/O write request to the shared storage so that I/O in the system can be controlled autonomously, if the current login node is not abnormal, an effective label is added to the I/O in the shared storage, otherwise, the label of the I/O is not updated.

In step S303, I/Os that do not update tags are discarded.

If the current node is abnormal and cannot execute the service request sent by the client, the I/O label of the current node is not updated, the I/O label of the current node is updated in the shared storage only when the current node is abnormal and can provide service, and when the VIP selects other nodes to execute the service request for the client again, the I/O of the label which is not updated before is discarded after the label information is updated in the shared storage by other nodes, so that the I/O of other nodes is not existed in the shared storage, and resource contention can be ensured.

The time of I/O fault switching can be shortened by setting the label information, a service scene with higher requirements on I/O fault switching can be met, the I/O in the system is independently controllable, the data written in by normal nodes can be ensured not to be covered, and the data consistency of the system is ensured. Compared with the method of the embodiment 2, in this embodiment, when the node is normal, the I/O of other nodes can be successfully terminated by discarding the expired I/O, and in the embodiment 2, the termination of the I/O may fail, and if the termination of the I/O fails, the SCST service or the entire physical node needs to be restarted.

Referring to FIG. 8, an embodiment of an apparatus for maintaining data consistency in an SCST storage system according to the invention will be described.

In an embodiment of the present invention, an apparatus for maintaining data consistency in an SCST storage system includes a determining module 801, an executing module 802, a storing module 803, and a writing module 804.

The judging module 801 is configured to query whether the system has an abnormal or other node login through the zookeeper after the current node logs in.

The execution module 802 is configured to terminate I/O for the current node to clear pending I/O for other nodes to perform I/O.

The determining module 801 is further configured to determine, by the current node, whether the I/O suspension duration is greater than a set duration; if yes, the current node restarts the SCST service or executes the node restart.

The judging module 801 is further configured to detect whether the I/O information of other nodes exists in the zookeeper when the current node logs in; and if so, the current node executes disconnection.

The execution module 802 is further configured to add a valid tag to all node I/O by zookeeper when the current node logs in, and notify the shared storage to update the valid tag, so as to complete the login.

The storage module 803 is used for the shared storage to receive the I/O write request of the current login node.

The write module 804 is configured to add tag information to the I/O write request for shared storage, and write the I/O of the current login node.

The storage module 803 is further configured to discard I/os with non-updated tags after the shared storage adds a valid tag to the I/O write request.

FIG. 9 illustrates a hardware block diagram of a computing device 90 for maintaining data consistency in an SCST storage system according to embodiments of the present description. As shown in fig. 9, computing device 90 may include at least one processor 901, storage 902 (e.g., non-volatile storage), memory 903, and a communication interface 904, and the at least one processor 901, storage 902, memory 903, and communication interface 904 are connected together via a bus 905. The at least one processor 901 executes at least one computer readable instruction stored or encoded in the memory 902.

It should be appreciated that the computer-executable instructions stored in the memory 902, when executed, cause the at least one processor 901 to perform the various operations and functions described above in connection with fig. 1-9 in the various embodiments of the present specification.

In embodiments of the present description, computing device 90 may include, but is not limited to: personal computers, server computers, workstations, desktop computers, laptop computers, notebook computers, mobile computing devices, smart phones, tablet computers, cellular phones, Personal Digital Assistants (PDAs), handheld devices, messaging devices, wearable computing devices, consumer electronics, and so forth.

According to one embodiment, a program product, such as a machine-readable medium, is provided. A machine-readable medium may have instructions (i.e., elements described above as being implemented in software) that, when executed by a machine, cause the machine to perform various operations and functions described above in connection with fig. 1-9 in the various embodiments of the present specification. Specifically, a system or apparatus may be provided which is provided with a readable storage medium on which software program code implementing the functions of any of the above embodiments is stored, and causes a computer or processor of the system or apparatus to read out and execute instructions stored in the readable storage medium.

According to the method and the application for keeping the data consistency in the SCST storage system, the abnormal condition of the system can be actively inquired through the zookeeper, the I/O of the current node can be cleared in time, all abnormal I/O can be cleared within the specified time, and the resource contention caused by the fact that the I/O of a plurality of nodes is written into the shared storage is avoided. The time for clearing the I/O can be shortened by setting the shared storage, the I/O controllability is ensured, and the data consistency of the system is further ensured.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.

Claims

1. A method for maintaining data consistency in an SCST storage system, comprising the steps of:

after the current node logs in, whether the system has abnormity or other nodes are logged in is inquired through the zookeeper; if so,

the current node aborts I/O to clear pending I/O for other nodes to perform I/O.

2. The method of maintaining data consistency in an SCST storage system according to claim 1, wherein said method further comprises:

the current node judges whether the duration of the I/O interruption is greater than the set duration;

and if so, restarting the SCST service by the current node or executing node restarting.

3. The method of maintaining data consistency in an SCST storage system according to claim 1, wherein said method further comprises:

the current node detects whether I/O information of other nodes exists in the zookeeper during login; if so,

the current node performs disconnection.

4. The method of maintaining data consistency in an SCST storage system according to claim 1, wherein said method further comprises:

and when the current node logs in, adding effective labels to all node I/O (input/output) through zookeeper, and notifying shared storage to update the effective labels so as to complete the logging.

5. A method for maintaining data consistency in an SCST storage system, comprising:

the shared storage receives an I/O write request of a current login node;

and the shared storage adds an effective label to the I/O write request and writes the effective label into the I/O of the current login node.

6. The method for maintaining data consistency in an SCST storage system according to claim 5, wherein said method further comprises:

discarding I/Os with non-updated tags after the shared store adds a valid tag to the I/O write request.

7. An apparatus for maintaining data consistency in an SCST storage system, the apparatus comprising:

the judging module is used for inquiring whether the system has abnormity or other node logins through the zookeeper after the current node logins; and

and the execution module is used for stopping I/O of the current node so as to clear the suspended I/O and enabling other nodes to execute I/O.

8. An apparatus for maintaining data consistency in an SCST storage system, the apparatus comprising:

the storage module is used for receiving an I/O (input/output) write request of a current login node by the shared storage; and

9. An electronic device, comprising:

at least one processor; and

memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform a method of maintaining data coherency in an SCST storage system according to any one of claims 1 to 6.

10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for maintaining data consistency in an SCST storage system according to any one of claims 1 to 6.