Distributed storage system abnormal node restart method and system

Abstract

The present invention provides a distributed storage system abnormal node restart method and system. The method comprises: each node in a storage cluster forms a monitoring ring; in the monitoring ring, each node starts monitoring an adjacent node; when a monitored node is detected to have a fault, the monitored node is restarted. The distributed storage system abnormal node restart method and system provided by the present invention can handle faults occurring in the distributed storage system in the first place.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed storage systems, and in particular to a method and system for restarting abnormal nodes in a distributed storage system. Background Art

[0002] With the development of Internet technology, the requirements for storage are gradually increasing. At present, the development of some key technologies is based on big data. This also makes the distributed storage system with easy expansion and large capacity popular in the market. However, because distributed storage stores data on different machine nodes, there will be many uncertainties. Some states can only be restored by restarting the node to restore the state of the node, thereby restoring the state of the cluster.

[0003] Existing technical solutions all rely on manual intervention to repair and restart nodes to achieve the purpose of restoring the cluster, and each distributed storage management platform can only prompt the user the cluster status and node status. The management platform itself cannot automatically restart the node. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for restarting abnormal nodes in a distributed storage system, which can handle faults occurring in the distributed storage system in the first time.

[0005] To solve the above technical problems, the present invention provides a method for restarting an abnormal node in a distributed storage system, the method comprising: each node in a storage cluster together forms a monitoring ring; in the monitoring ring, each node starts monitoring an adjacent node; when a failure of the monitored node is detected, the monitored node is restarted.

[0006] In some implementations, the method further includes: before each node starts monitoring a neighboring node, setting an address of the monitored node.

[0007] In some implementations, the further step includes: before each node starts monitoring a neighboring node, setting a user name and password of the monitored node.

[0008] In some implementations, when a monitored node is detected to have a fault, the monitored node is restarted, including: when a monitored node is detected to have a fault, the monitored node is restarted through an IPMI interface.

[0009] In some implementations, the management platform restarts the monitored node.

[0010] In some implementations, the nodes in the storage cluster together constitute a management platform.

[0011] In addition, the present invention also provides a distributed storage system abnormal node restart system, the system comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the distributed storage system abnormal node restart method according to the above-mentioned.

[0012] After adopting such a design, the present invention has at least the following advantages:

[0013] By forming a storage ring with each storage node in the distributed storage system, and each storage node monitors a storage node adjacent to it in the storage ring, when a fault is detected, the monitoring node is restarted through the IPMI interface, so that the storage system can handle the fault in the system as soon as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0015] Figure 1 Schematic diagram of the system architecture of a system for restarting an abnormal node in a distributed storage system provided by an embodiment of the present invention;

[0016] Figure 2 The present invention is a flowchart of a method for restarting an abnormal node in a distributed storage system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] Figure 1 The overall network architecture of the distributed storage system is shown in Figure 1. Figure 1 The distributed storage system includes a plurality of independent storage nodes 12. Moreover, these storage nodes 12 together form a storage ring 11.

[0019] It is understandable that, on the storage ring 11, each storage node 12 has two adjacent storage nodes 12. When performing adjacent node monitoring, each storage node 12 monitors one of the two adjacent nodes. Moreover, on the storage ring 11, each storage node 12 monitors one adjacent storage node 12, and each storage node 12 is monitored by one adjacent storage node 12. In other words, there will be no phenomenon that one node 12 is monitored repeatedly by two nodes 12 at the same time.

[0020] In the storage ring 11, all storage nodes 12 together form a management platform for managing the storage system. More specifically, a management component is installed inside each storage node 12, and the management functions of the entire storage system are implemented through the cooperation of management components on different nodes. These management functions may include: deleting nodes from the existing storage ring 11, adding nodes to the storage ring 11, allocating storage space among all storage nodes 12, load balancing external access traffic, etc.

[0021] When monitoring the adjacent node 12, the storage node 12 monitors the adjacent node through its own IPMI interface. Once it is found that the monitored adjacent node fails, the monitoring node will restart the monitored node that has failed. After the above-mentioned restart operation, there will be no more failed nodes on the storage ring 11, and the storage system is still working normally.

[0022] Furthermore, the above monitoring process also includes parameter setting operations. Figure 2 Before each node on the storage ring monitors each other, the user can also set the IPMI address, IPMI user name and password of each node through the management system. After the above operation is set, the monitored node can identify whether the node sending the restart instruction is the target node through the above setting parameters, which improves the security of system operation.

[0023] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Those skilled in the art may make some simple modifications, equivalent changes or modifications using the technical contents disclosed above, which all fall within the protection scope of the present invention.

Claims

1. A method for restarting an abnormal node in a distributed storage system, characterized in that: include: The monitoring ring is composed of each node in the storage cluster; In the monitoring ring, each node starts monitoring an adjacent node; When a monitored node fails, the monitored node is restarted; The management platform restarts the monitored node; The nodes in the storage cluster together form a management platform; A management component is installed inside each storage node, and the management function of the entire storage system is realized through the cooperation of management components on different nodes.

2. The method for restarting an abnormal node in a distributed storage system according to claim 1, characterized in that: Also includes: Before each node starts monitoring an adjacent node, the address of the monitored node is set.

3. The method for restarting an abnormal node in a distributed storage system according to claim 1, characterized in that: Also includes: Before each node starts monitoring an adjacent node, set the user name and password of the monitored node.

4. The method for restarting an abnormal node in a distributed storage system according to claim 1, characterized in that: When a monitored node fails, the monitored node is restarted, including: When a monitored node fails, the monitored node is restarted through the IPMI interface.

5. A distributed storage system abnormal node restart system, characterized in that: include: A plurality of storage nodes, each of which is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method for restarting an abnormal node in a distributed storage system according to any one of claims 1 to 4.

Images