Fault processing method, computer equipment, expansion hard disk equipment and distributed storage system

Abstract

The embodiment of the invention provides a fault processing method, computer equipment, expansion hard disk equipment and a distributed storage system, and belongs to the technical field of computing equipment.The method comprises the steps that health information of a first link and health information of a second link are obtained from the expansion hard disk equipment; the first computing device and the second computing device are data nodes of the distributed storage system; the first link is a data transmission link; the second link is a standby data transmission link; determining the state of the first link based on the health information of the first link, and determining the state of the second link based on the health information of the second link; under the condition that the state of the first link is the fault state and the state of the second link is the normal state, the second link is controlled to be switched to serve as the data transmission link, and the system fault processing method solves the problem that when the distributed storage system breaks down, the fault processing efficiency is low, and consequently the system fault processing time is long.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computing devices, and particularly relates to a fault processing method, a computer device, an expansion hard disk device and a distributed storage system. BACKGROUND

[0002] The distributed storage system is a technology of storing data on a group of nodes or servers, that is, distributing the interaction data between the user end and the server on multiple different servers, and then managing, accessing and storing data through the network between the nodes.

[0003] In the related art, the distributed storage system includes a client, a central node server and multiple general servers, and at least one storage hard disk is mounted on each general server. The processing business surfaces of each general server do not interfere with each other. Therefore, when one of the general servers fails, the storage hard disk mounted on the general server cannot be accessed, and the storage cluster software deployed in the distributed storage system needs to spend a lot of time and computing power to complete data recovery, such as using data backup. However, in the distributed storage system, a large amount of replication data needs to be transmitted, which affects the overall performance of the system, is inefficient, and leads to the problem of long system fault processing time.

[0004] Therefore, how to quickly complete data recovery when the distributed storage system fails is a problem to be solved. SUMMARY

[0005] Embodiments of the present application provide a fault processing method, a computer device, an expansion hard disk device and a distributed storage system, which can improve the fault processing efficiency.

[0006] In a first aspect, the embodiments of the present application provide a fault processing method applied to a first computing device, and the method comprises:

[0007] obtaining health information of a first link and health information of a second link from an expansion hard disk device; wherein the first link is a serial connection SCSI link between the first computing device and the expansion hard disk device; the second link is a serial connection SCSI link between a second computing device and the expansion hard disk device; the first computing device and the second computing device are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a standby data node; the first link is a data transmission link; and the second link is a standby data transmission link;

[0008] determining a state of the first link based on the health information of the first link, and determining a state of the second link based on the health information of the second link;

[0009] in a case where the state of the first link is a fault state and the state of the second link is normal, controlling to switch the second link as a data transmission link.

[0010] In the method, the first link health information between the first computing device and the expansion hard disk and the second link health information between the second computing device and the expansion hard disk are obtained from the expansion hard disk device, and then the states of the first link and the second link are obtained based on the first link health information and the second link health information, so that the second link is controlled to be switched as the data transmission link when the state of the first link is the fault state and the state of the second link is normal, thereby enabling the data access of the expansion hard disk device mounted by a first computing device in a distributed storage system to be quickly implemented through the second link after the first computing device fails, improving the fault processing efficiency and reducing the fault processing time.

[0011] In a possible implementation, when the state of the first link is the fault state and the state of the second link is normal, the second link is controlled to be switched as the data transmission link, including: sending a switching notification to the second computing device when the state of the first link is the fault state and the state of the second link is normal; the switching notification is used to trigger the second computing device to send a switching instruction to the expansion hard disk device; the switching instruction is used to instruct the expansion hard disk device to switch the second link as the data transmission link.

[0012] In a possible implementation, before the health information of the first link and the health information of the second link are obtained from the expansion hard disk device, the method includes: sending a first serial management protocol (SMP) command to the expansion hard disk; the first SMP command is used to instruct to obtain the health information of the first link and the health information of the second link.

[0013] In a second aspect, an embodiment of the present application provides a fault processing method, applied to an expansion hard disk device, and the method includes:

[0014] receiving a first serial management protocol (SMP) command from a first computing device; the first SMP command is used to instruct to obtain health information of a first link and health information of a second link; wherein the first link is a serial connection SCSI (Small Computer System Interface) link between the first computing device and the expansion hard disk device; the second link is a serial connection SCSI link between a second computing device and the expansion hard disk device; the first computing device and the second computing device are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a standby data node; the first link is a data transmission link; and the second link is a standby data transmission link;

[0015] in response to the first SMP command, sending the health information of the first link and the health information of the second link to the first computing device.

[0016] In the method, a first serial management protocol (SMP) command sent by the first device is received, and in response to the first SMP command, health information of the first link and health information of the second link are sent to the first computing device.

[0017] In a possible implementation, the method further includes: receiving a second SMP command from the second computing device; the second SMP command is used to instruct to acquire the health information of the first link and the health information of the second link.

[0018] In response to the second SMP command, the health information of the first link and the health information of the second link are sent to the second computing device.

[0019] In a possible implementation, the method further includes: receiving a switching command; the switching command is used to instruct to switch the second link as a data transmission link; in response to the switching command, a first serial attached SCSI (SAS) region is switched to a second SAS region; the first SAS region is a logical storage region corresponding to the first link; and the second SAS region is a logical storage region corresponding to the second link.

[0020] In a possible implementation, the method further includes: triggering a soft restart of the expansion hard disk device.

[0021] In a third aspect, an embodiment of the present application provides a computing device, the computing device including a first memory and a processor; the first memory and the processor are coupled; the first memory is configured to store computer instructions; and the processor is configured to execute the computer instructions to enable the computing device to perform the fault processing method described in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides an expansion hard disk device, the expansion hard disk device including a second memory and a controller; the second memory and the controller are coupled; the second memory is configured to store computer instructions; and the controller is configured to execute the computer instructions to enable the expansion hard disk device to perform the fault processing method described in the second aspect.

[0023] In a fifth aspect, an embodiment of the present application provides a distributed storage system, the distributed storage system including a first computing device, a second computing device, and an expansion hard disk group; the first computing device and the second computing device are respectively coupled with an expansion hard disk device.

[0024] The first computing device and / or the second computing device are the computing device described in the third aspect.

[0025] The expansion hard disk device is the expansion hard disk device described in the fourth aspect. BRIEF DESCRIPTION OF DRAWINGS

[0026] Figure 1 An application scenario diagram of a fault processing method provided by an embodiment of the present application is shown.

[0027] Figure 2 A flowchart illustrating a fault handling method provided in this application embodiment. Figure One ;

[0028] Figure 3 A flowchart illustrating a fault handling method provided in this application embodiment. Figure Two ;

[0029] Figure 4 A schematic diagram of the data transmission logic of the fault handling method provided in the embodiments of this application;

[0030] Figure 5 A schematic diagram of the interaction flow of a fault handling method provided in an embodiment of this application;

[0031] Figure 6 A schematic diagram of the structure of a fault handling device provided in an embodiment of this application. Figure One ;

[0032] Figure 7 A schematic diagram of the structure of a fault handling device provided in an embodiment of this application. Figure Two .

[0033] Explanation of reference numerals in the attached figures:

[0034] 11-Client; 12-First Name Node Server; 13-Second Name Node Server; 14-First Computing Device; 15-Second Computing Device; 16-Extended Hard Disk Device. Detailed Implementation

[0035] Example 1:

[0036] Figure 1 This is a schematic diagram illustrating an application scenario of a fault handling method provided in an embodiment of this application.

[0037] like Figure 1 As shown, this application scenario includes a client 11 of the HDFS distributed file system, a first name node server 12, a second name node server 13, multiple first computing devices 14, multiple second computing devices 15, and multiple extended hard disk devices 16. The client 11 is communicatively connected to both the first name node server 12 and the second name node server 13, with the second name node server 13 serving as a backup server for the first name node server 12. Both the first computing devices 14 and the second computing devices 15 can be servers, and the online first name node server 12 and the second name node server 13 are communicatively connected to both the multiple first computing devices 14 and the multiple second computing devices 15. Each first computing device 14 and each second computing device 15 is coupled to the same extended hard disk device 16.

[0038] In this embodiment, the communication connection can be an interactive protocol based on the HDFS communication protocol, wherein the HDFS communication protocol is based on the TCP / IP protocol, that is, the client 11 is connected to the first and second name node servers 12 and 13 through a configurable TCP port to realize interaction. The first name node server 12 and the first and second computing devices 14 and 15 can use the Data Node Protocol to realize communication connection and interaction. The distributed storage can be realized by dispersing data on different expansion hard disk devices, so as to

[0039] Embodiment two:

[0040] Figure 2 Flowchart of a fault processing method provided in the embodiment of the application Figure One The application is applied to a first computing device in an application scenario as shown in Figure 1 The method comprises the following steps.

[0041] S201: Obtain health information of a first link and health information of a second link from an expansion hard disk device; wherein the first link is a serial connection SCSI link between the first computing device and the expansion hard disk device; the second link is a serial connection SCSI link between the second computing device and the expansion hard disk device; the first and second computing devices are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a standby data node; the first link is a data transmission link; and the second link is a standby data transmission link.

[0042] In this embodiment, the expansion hard disk device can be a JBOD (just a bunch of disks, hard disk storage expansion cabinet). The chassis of the JBOD is integrated with a large number of hard disks through a SAS Expander in the SAS protocol, and provides a connection protocol input port for the first or second computing device coupled with the expansion hard disk device. The expansion hard disk device provides a low-cost and expandable storage infrastructure for the distributed storage system.

[0043] In the embodiment, the working data node refers to a source of storage capacity of the HDFS cluster of the distributed storage system and an execution node that is performing actual data read and write operations. The file submitted by the user is split into data blocks of fixed size, and each data block is stored in the form of an independent file on the extended hard disk device connected to the working data node through the serial attached SCSI link. The second computing device refers to a backup data node, which is an execution node that backs up the working data node, and the working data node and the backup data node are connected to the same extended hard disk device. When the first link fails and data read and write operations cannot be performed, the backup data node can be quickly switched to perform read and write operations, and the second link is used to read and write data blocks from the extended hard disk device.

[0044] In the embodiment, the storage cluster software is deployed on the first computing device and the second computing device, and the software is used to monitor and arbitrate the first link and the second link. The deployment manner can be logging in a web link of the storage cluster software or a cloud platform on the first computing device and the second computing device.

[0045] S202: determining the state of the first link based on the health information of the first link and determining the state of the second link based on the health information of the second link.

[0046] In the embodiment, the determination of the state of the first link based on the health information of the first link can be performed by detecting whether the data transmission signal of the first link is stable. The health information of the first link can include a time period of collected signals and collected signal data. For example, when there is no heartbeat signal in a certain time period, it is determined that the state of the first link is a link failure state. Similarly, the determination of the state of the second link based on the health information of the second link can also be a process of judging link failure or link normality according to the signal data collected in a fixed time period.

[0047] S203: in the case that the state of the first link is a failure state and the state of the second link is a normal state, the second link is controlled to be switched as a data transmission link.

[0048] In the embodiment, the case that the state of the first link is a failure state and the state of the second link is a normal state indicates that the first computing device cannot read the extended hard disk group through the first link. If the normal operation of the distributed storage system is to be maintained, the second link can be controlled to be switched as a data transmission link, so as to perform the operation of reading data from the extended hard disk group through the second computing device.

[0049] Based on the above embodiment, in an optional embodiment of the present application, step S203 specifically includes:

[0050] In a case that the state of the first link is a failure state and the state of the second link is normal, a switching notification is sent to the second computing device; the switching notification is used to trigger the second computing device to send a switching instruction to the expansion hard disk device; the switching instruction is used to instruct the expansion hard disk device to switch the second link as a data transmission link.

[0051] In the embodiment, the sending of the switching notification to the second computing device can be that the storage cluster software controls the second computing device to send the switching notification to the expansion hard disk device through the second link, so that the expander SASExpander in the expansion hard disk device executes the switching instruction.

[0052] In an optional embodiment of the present application, before the obtaining of the health information of the first link and the health information of the second link from the expansion hard disk device in step S201, the method further includes: sending a first serial management protocol (SMP) command to the expansion hard disk; the first SMP command is used to instruct the obtaining of the health information of the first link and the health information of the second link.

[0053] In the embodiment, the first computing device and the second computing device can periodically send a self-defined command, i.e., a first serial management protocol (SMP) command, to the expander SASExpander of the expansion hard disk device; an in-built thread of the expander performs the periodic detection of the first link and the second link; when the thread receives the first SMP command, the thread executes the first SMP command to collect the health information of the first link and the health information of the second link, and then reports the health information of the first link and the health information of the second link to the storage cluster software deployed in the first computing device and the second computing device, so that the storage cluster software discovers whether the first link and the second link are abnormal.

[0054] In an optional embodiment of the present application, the sending of the first SMP command to the expansion hard disk can be achieved by using an in-band periodic polling manner; the in-band periodic polling can be that the first computing device and the second computing device send the self-defined SMP command through a normal first serial port at a fixed period and a fixed frequency, so as to collect the health information of the first link and the health state information of the second link from the expander SASExpander, instead of passively waiting for the expander SASExpander to map the health information of the first link and the health information of the second link.

[0055] In summary, the fault processing method provided by the embodiments of the present application first obtains the health information of the first link and the second link in a backup relationship from the expansion hard disk device, and then determines the state of the first link and the state of the second link based on the health information of the first link and the health information of the second link. When the first link is in a fault state and the second link is in a normal state, the second link is controlled to be switched as a data transmission link, which reduces the fault explosion radius and avoids the system from resuming normal operation after a large amount of replicated data is transmitted in the distributed storage network, thereby saving the fault processing time and improving the fault processing efficiency.

[0056] Meanwhile, the first computing device corresponding to the first link fault or the second computing device corresponding to the second link fault can be determined more quickly through the heartbeat signal, further improving the efficiency and accuracy of the fault determination result.

[0057] Meanwhile, the health information of the first link and the health information of the second link are detected and updated in real time through periodic polling of the expansion hard disk group, so that the fault in the distributed storage system can be found at the first time, the troubleshooting time after the fault occurs is reduced, and the fault processing efficiency is further improved.

[0058] Embodiment Three

[0059] Figure 3 Flowchart of the fault processing method provided by the embodiments of the present application Figure Two , applied to an expansion hard disk device in an application scenario as shown in Figure 1 , the method comprises the following steps:

[0060] S301: receiving a first serial management protocol (SMP) command from a first computing device; the first SMP command is used to instruct to obtain the health information of the first link and the health information of the second link; wherein the first link is a serial connection SCSI (Small Computer System Interface) link between the first computing device and the expansion hard disk device; the second link is a serial connection SCSI link between the second computing device and the expansion hard disk device; the first computing device and the second computing device are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a backup data node; the first link is a data transmission link; and the second link is a backup data transmission link.

[0061] In the embodiment, the expansion hard disk device receives the first serial management protocol SMP command from the first computing device through the first link. That is, the expansion hard disk device only monitors and reports the health status of the first link and the second link, and does not participate in the decision of switching between the first link and the second link as a passive device. The first serial management protocol SMP command, the health information of the first link and the health information of the second link are all completed in the SAS band, which can meet the requirement of switching between the first computing device and the second computing device in minutes when a fault occurs. When the health information of the first link and the switching command are completed by means of the second link of the opposite end, all signals and instructions are completed in the SAS band.

[0062] S302: In response to the first SMP command, the health information of the first link and the health information of the second link are sent to the first computing device.

[0063] In the embodiment, after the expansion hard disk device receives the first serial management protocol SMP command, the health information of the first link and the health information of the second link are collected in response to the first SMP command. The first serial management protocol SMP command can be transmitted in the form of a SAS heartbeat signal in the first link. When the thread for periodically detecting the first link and the second link established by the expander SASExpander in the expansion hard disk group is executed, the health information of the first link and the health information of the second link are automatically generated and mapped to the first computing device.

[0064] The process after the health information of the first link and the health information of the second link are mapped to the first computing device has been specifically described in Embodiment 1, so this embodiment will not be repeated here.

[0065] On the basis of the above-mentioned embodiments, the fault processing method provided as an optional embodiment of the present application further comprises:

[0066] Step A: receiving a second SMP command from the second computing device; the second SMP command is used to instruct to obtain the health information of the first link and the health information of the second link.

[0067] In the embodiment, the second computing device also periodically sends the second SMP command to the expansion hard disk device from the second link to complete the in-band periodic polling of the expander SASExpander of the expansion hardware device, so that the second computing device obtains the health information of the first link and the health information of the second link.

[0068] Step B: in response to the second SMP command, the health information of the first link and the health information of the second link are sent to the second computing device.

[0069] In the embodiment, the second SMP command can be a heartbeat signal, which is transmitted to the expansion hard disk device through the second link. When the thread for periodically detecting the first link and the second link, which is established in advance by the SAS expander in the expansion hard disk group, is executed, the health information of the first link and the health information of the second link are automatically generated and mapped to the second computing device.

[0070] Based on the above embodiment, in an optional embodiment of the present application, the fault processing method further comprises:

[0071] Step C: receiving a switching command; the switching command is used to indicate switching the second link as a data transmission link.

[0072] In the embodiment, the switching command can be a computer executable instruction sent by the first computing device through the first link. The switching command refers to an instruction for controlling the SAS expander in the expansion hard disk group to perform SAS area switching. After the SAS area switching, the link for corresponding data reading and writing is switched from the first link to the second link.

[0073] Step D: switching the first serial connection SCSI SAS area to the second SAS area in response to the switching command; wherein the first SAS area is a logical storage area corresponding to the first link; and the second SAS area is a logical storage area corresponding to the second link.

[0074] In the embodiment, the first SAS area and the second SAS area can both be used to store user uploaded data. The switching of the first SAS area to the second SAS area can be achieved by controlling the serial connection management chip to perform area switching operation in response to the switching command, for example, modifying the logical storage area configuration, and modifying the area configuration parameter of the first SAS area to the area configuration parameter corresponding to the second SAS area.

[0075] In an optional embodiment of the present application, the fault processing method further comprises:

[0076] Step E: triggering a soft restart of the expansion hard disk device.

[0077] In the embodiment, the soft restart refers to not cutting off the power supply of the device, but only reinitializing the key components through software quality, so as to minimize the system interruption time and maintain the normal operation state of part of the functions.

[0078] Figure 4 The data transmission logic diagram of the fault processing method provided in the embodiment of the present application.

[0079] As Figure 4As shown, the first computing device and the second computing device are both deployed with storage cluster software, and the storage cluster software is used to monitor the failure states of the first link and the second link when the first link is in a failure state and the second link is in a normal state. The specific process is as follows:

[0080] First, the first link of the first computing device and the second link of the second device are detected in real time. The first computing device sends a heartbeat signal to the expansion hard disk device at a regular time. The heartbeat signal is formed in the form of a first serial management protocol (SMP) command, and is input into an expander SASExpander in the expansion hard disk device through a first serial link SCSI signal interface 1, so that the SASExpander executes a thread to collect health information of the first link and health information of the second link. Then the health information of the first link and the health information of the second link are returned to the first computing device. Similarly, the second computing device also acquires the health information of the first link and the health information of the second link through the above-mentioned manner.

[0081] When the storage cluster software determines that the first link is in a failure state and the second link is in a normal state based on the health information of the first link and the health information of the second link, a switching command is sent to the expansion hard disk device through the first computing device and the second computing device, so that the expander SASExpander executes the switching command to switch the current first SAS area of the expansion hard disk device to a second SAS area.

[0082] In summary, the failure processing method provided by the embodiment of the present application can send the health information of the first link and the health information of the second link to the first computing device and the second computing device after receiving the first serial management protocol (SMP) command sent by the first computing device, and switch the first serial link SCSI SAS area to the second SAS area after receiving the switching command. When a failure occurs, since data is transmitted in-band through SAS and is an end-to-end path, there is no third party such as BMC or third party network such as 1G management network of the machine room cabinet to interfere, and the switching between the data transmission link and the standby data transmission link can be completed in the shortest time. Compared with the requirement of second-level dual-computer switching when the centralized storage fails, the switching based on the distributed storage can be completed in minutes, and the main time consumption is the time of polling the health information of the first link and the health information of the second link by the storage software and the time of scanning and reporting HDD topology information on the server by the SASExpander after the SAS area switching.

[0083] Embodiment four:

[0084] Figure 5 An interaction flow diagram of the failure processing method provided by the embodiment of the present application.

[0085] AsFigure 5 As shown in the figure, the interactive flow of the fault processing method includes the following steps:

[0086] S501, the first computing device sends a first serial management protocol (SMP) command to the expansion hard disk device.

[0087] S502, the expansion hard disk device sends the health information of the first link and the health information of the second link to the first computing device in response to the first SMP command.

[0088] S503, the first computing device determines the state of the first link based on the first link, and determines the state of the second link based on the health information of the second link.

[0089] S504, the first computing device sends a switching command to the expansion hard disk device in the case that the state of the first link is a fault state and the state of the second link is a normal state.

[0090] S505, the expansion hard disk device switches the first serial connection SCSI (SCSI) area to the second SCSI area in response to the switching command, and triggers a soft restart of the expansion hard disk device.

[0091] Embodiment five:

[0092] Figure 6 The structure of a fault processing device provided by the embodiment of the application Figure One .

[0093] As Figure 6 shown, the embodiment of the application further provides a fault processing device applied to a first computing device, which includes a data transmission module 61, a link state determination module 62, and a switching module 63.

[0094] The data transmission module 61 is used to obtain the health information of a first link and the health information of a second link from an expansion hard disk device; wherein the first link is a serial connection SCSI (SCSI) link between the first computing device and the expansion hard disk device; the second link is a serial connection SCSI link between a second computing device and the expansion hard disk device; the first computing device and the second computing device are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a standby data node; the first link is a data transmission link; and the second link is a standby data transmission link.

[0095] The link state determination module 62 is used to determine the state of the first link based on the health information of the first link, and determine the state of the second link based on the health information of the second link.

[0096] The switching module 63 is configured to control switching the second link as the data transmission link when the state of the first link is the fault state and the state of the second link is the normal state.

[0097] In an optional embodiment of the present application, the switching module 53 is specifically configured to: send a switching notification to the second computing device when the state of the first link is the fault state and the state of the second link is normal; and trigger the second computing device to send a switching instruction to the expansion hard disk device, wherein the switching instruction is used to instruct the expansion hard disk device to switch the second link as the data transmission link.

[0098] In an optional embodiment of the present application, the link information transmission module 61 is further configured to: send a first serial management protocol (SMP) command to the expansion hard disk device before acquiring the health information of the first link and the health information of the second link from the expansion hard disk device, wherein the first SMP command is used to instruct to acquire the health information of the first link and the health information of the second link.

[0099] The fault processing apparatus provided in the embodiment can be used to execute the fault processing method in the second method embodiment, and has similar implementation principles and technical effects, which are not described here in detail.

[0100] Embodiment six

[0101] Figure 7 The structure of the fault processing apparatus provided in the embodiment of the present application is shown in Figure Two .

[0102] As Figure 7 shown, the embodiment of the present application further provides a fault processing apparatus applied to an expansion hard disk device, which comprises a command receiving module 71 and a data sending module 72.

[0103] The command receiving module 71 is configured to receive a first serial management protocol (SMP) command from a first computing device, wherein the first SMP command is used to instruct to acquire health information of a first link and health information of a second link; the first link is a serial connection SCSI link between the first computing device and the expansion hard disk device; the second link is a serial connection SCSI link between a second computing device and the expansion hard disk device; the first computing device and the second computing device are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a standby data node; the first link is a data transmission link; and the second link is a standby data transmission link.

[0104] The data sending module 72 is configured to send the health information of the first link and the health information of the second link to the first computing device in response to the first SMP command.

[0105] In an optional embodiment of the present application, the command receiving module 71 is further configured to receive a second SMP command from the second computing device, the second SMP command being configured to instruct to obtain the health information of the first link and the health information of the second link; and the data sending module 72 is further configured to send the health information of the first link and the health information of the second link to the second computing device in response to the second SMP command.

[0106] In an optional embodiment of the present application, the command receiving module 71 is further configured to receive a switching command, the switching command being configured to instruct to switch the second link as a data transmission link; and in response to the switching command, switch the first serial attached SCSI (SAS) region to a second SAS region, the first SAS region being a logical storage region corresponding to the first link, and the second SAS region being a logical storage region corresponding to the second link.

[0107] In an optional embodiment of the present application, the command receiving module 71 is further configured to trigger a soft restart of the expansion hard disk device.

[0108] The fault processing apparatus provided in the embodiment can be used to execute the fault processing method in the above-mentioned method embodiment three, and has similar implementation principles and technical effects, which are not described here in detail.

[0109] Embodiment seven:

[0110] The embodiment of the present application further provides a computing device, which comprises a first memory and a processor; the first memory and the processor are coupled;

[0111] The first memory is configured to store computer instructions;

[0112] The processor is configured to execute the computer instructions, so that the computing device executes the fault processing method as described in the above-mentioned embodiment two.

[0113] Embodiment eight:

[0114] The embodiment of the present application further provides an expansion hard disk device, which comprises a second memory and a controller; the second memory and the controller are coupled;

[0115] The second memory is configured to store computer instructions;

[0116] The controller is configured to execute the computer instructions, so that the expansion hard disk device executes the fault processing method as described in the above-mentioned embodiment three.

[0117] Embodiment nine:

[0118] The embodiment of the present application further provides a distributed storage system, comprising a first computing device, a second computing device and a hard disk expansion group; wherein the first computing device and the second computing device are coupled with the expansion hard disk device respectively. In the embodiment, the first computing device and / or the second computing device are the computing device in the seventh embodiment, and the expansion hard disk device is the expansion hard disk device in the sixth embodiment.

[0119] Optionally, the controller can be a processor such as a central processing unit (CPU), and can also be a graphics processing unit (GPU), other general-purpose processor, a digital signal processor (DSP), or an application specific integrated circuit (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0120] The embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores computer program instructions; the computer program instructions are executed by an electronic device or a computing device, so that the electronic device or the computing device executes the fault processing method.

[0121] The embodiment of the present application provides a computer program product, and the computer program product comprises computer program instructions; when the computer program instructions are executed, the electronic device or the computing device executes the fault processing method.

[0122] All or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the foregoing memory (storage medium) comprises: a read-only memory (English: read-only memory, abbreviation: ROM), a RAM, a flash memory, a hard disk, a solid state disk, a magnetic tape (English: magnetic tape), a floppy disk (English: floppy disk), an optical disc (English: optical disc) and any combination thereof.

[0123] The embodiments of the present application are described with reference to the flowchart illustrations and / or block diagrams of the methods, apparatus (systems) and computer program products according to the embodiments of the present application. It is understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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 illustrations and / or block diagrams block or blocks. Figure One one or more flowcharts and / or blocks Figure One one or more flowcharts and / or blocks

[0124] These computer program instructions can 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 instructions which implement the function specified in the flowchart illustrations and / or block diagrams block or blocks. Figure One one or more flowcharts and / or blocks Figure One one or more flowcharts and / or blocks

[0125] These computer program instructions can 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 illustrations and / or block diagrams block or blocks. Figure One one or more flowcharts and / or blocks Figure One Figure One one or more flowcharts and / or blocks

[0126] Obviously, persons having ordinary skill in the art can be able to make various modifications and variations to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, the embodiments of the present application are also intended to cover these modifications and variations of the embodiments of the present application which are within the scope of the claims of the present application and their equivalents.

[0127] In the embodiments of the present application, the terms "comprising", "containing" or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element. The term "or" and its variants can refer to "and / or". In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. In the embodiments of the present application, "a plurality of" means two or more. "And / or", which describes the relationship between the associated objects, means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects.

[0128] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the embodiments of the present application cover any and all variations of the present application that lie within the scope of the general inventive concepts herein, along with all of the alterations and further modifications of the embodiments of the present application that are disclosed and that can fall out by the usual practice of the art to which the embodiments of the present application pertains.

Claims

1. A fault handling method, applied to a first computing device, characterized in that, The method comprises: obtaining health information of a first link and health information of a second link from an expansion hard disk device; wherein the first link is a serial connection SCSI link between the first computing device and the expansion hard disk device; the second link is a serial connection SCSI link between the second computing device and the expansion hard disk device; the first computing device and the second computing device are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a standby data node; the first link is a data transmission link; and the second link is a standby data transmission link; determining a state of the first link based on the health information of the first link, and determining a state of the second link based on the health information of the second link; in a case where the state of the first link is a fault state and the state of the second link is a normal state, controlling switching of the second link as a data transmission link.

2. The failure handling method according to claim 1, characterized by, The method further comprises: in a case where the state of the first link is a fault state and the state of the second link is a normal state, sending a switching notification to the second computing device; the switching notification is used to trigger the second computing device to send a switching instruction to the expansion hard disk device; the switching instruction is used to instruct the expansion hard disk device to switch the second link as a data transmission link.

3. The failure handling method according to claim 1 or 2, characterized by, The method further comprises: sending the first serial management protocol SMP command to the expansion hard disk; the first SMP command is used to instruct obtaining the health information of the first link and the health information of the second link.

4. A failure processing method applied to an extended hard disk device, characterized by, The method comprises: receiving a first serial management protocol SMP command from a first computing device; the first SMP command is used to instruct obtaining health information of a first link and health information of a second link; wherein the first link is a serial connection SCSI link between the first computing device and an expansion hard disk device; the second link is a serial connection SCSI link between the second computing device and the expansion hard disk device; the first computing device and the second computing device are data nodes of a distributed storage system; the first computing device is a working data node; the second computing device is a standby data node; the first link is a data transmission link; and the second link is a standby data transmission link; in response to the first SMP command, sending the health information of the first link and the health information of the second link to the first computing device.

5. The failure handling method according to claim 4, characterized by, The method further comprises: receiving a second SMP command from the second computing device; the second SMP command is used to instruct obtaining the health information of the first link and the health information of the second link; in response to the second SMP command, sending the health information of the first link and the health information of the second link to the second computing device.

6. The failure handling method according to claim 4 or 5, characterized by, The method further comprises: receiving a switching command; the switching command is used to instruct switching the second link as a data transmission link; in response to the switching command, switching a first serial attached SCSI (SAS) area to a second SAS area; wherein the first SAS area is a logical storage area corresponding to the first link; and the second SAS area is a logical storage area corresponding to the second link.

7. The fault handling method of claim 6, wherein, The method further comprises: triggering a soft restart of the expansion hard disk device.

8. A computing device, comprising: The computing device comprises a first memory and a processor; the first memory and the processor are coupled; The first memory is used to store computer instructions; The processor is used to execute the computer instructions, so that the computing device executes the fault processing method according to any one of claims 1 to 3.

9. An extended hard disk device, characterized by comprising: The expansion hard disk device comprises a second memory and a controller; the second memory and the controller are coupled; The second memory is used to store computer instructions; The controller is used to execute the computer instructions, so that the expansion hard disk device executes the fault processing method according to any one of claims 4 to 7.

10. A distributed storage system, characterized by, The distributed storage system comprises a first computing device, a second computing device and a hard disk expansion group; wherein the first computing device and the second computing device are respectively coupled with the expansion hard disk device; The first computing device and / or the second computing device are the computing device according to claim 8; The expansion hard disk device is the expansion hard disk device according to claim 9.

Images