RDMA network configuration management method, device, equipment, medium and product

Abstract

The invention discloses an RDMA network configuration management method, device, equipment, medium and product, a main node is responsible for unified issuing of RDMA synchronous configuration information in the same RDMA cluster, the consistency of RDMA network configuration among different nodes in the RDMA cluster can be ensured, local RDMA configuration information and local RDMA operation indexes are detected regularly, and the reliability of RDMA network configuration management is improved. According to the method, the local RDMA configuration information or the local RDMA operation index is detected, and when the abnormal event is detected to exist in the local RDMA configuration information or the local RDMA operation index, the abnormal event is processed according to the preset exception processing strategy, so that the RDMA network configuration exception or the operation index exception of each node can be detected and processed in time, and the stable and efficient operation of the RDMA network can be ensured.

Description

Technical Field

[0001] This invention relates to the field of data transmission technology, and in particular to an RDMA network configuration management method, apparatus, electronic device, computer-readable storage medium, and computer program product. Background Technology

[0002] RDMA (Remote Direct Memory Access) is a high-performance network communication technology with advantages such as high bandwidth, low latency, and no CPU (Central Processing Unit) consumption. Current technologies for RDMA network configuration management typically check the RDMA network configuration information of numerous devices to ensure consistency and reconfigure RDMA parameters for devices with inconsistent configurations. However, considering the complexity and volatility of RDMA networks, simply checking the consistency of RDMA network configurations between individual devices during RDMA network configuration management is insufficient to guarantee the stable and efficient operation of the RDMA network. Summary of the Invention

[0003] This invention provides an RDMA network configuration management method, apparatus, device, medium, and product to solve the technical problem that existing RDMA network configuration management methods cannot guarantee the stable and efficient operation of RDMA networks.

[0004] To address the aforementioned technical problems, a first aspect of this invention provides an RDMA network configuration management method, comprising: According to the preset detection cycle, the local RDMA configuration information and local RDMA operation indicators are detected; wherein, the local RDMA configuration information is determined based on the RDMA synchronization configuration information issued by the master node in the same RDMA cluster. When an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicators, the abnormal event is handled according to a preset abnormality handling strategy.

[0005] As a preferred embodiment, when an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicators, the abnormal event is processed according to a preset abnormality handling strategy, specifically including: When an abnormal event is detected in the local RDMA configuration information, and the abnormal event is the loss of the local RDMA configuration information, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information. When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

[0006] As a preferred embodiment, when an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicator, the abnormal event is processed according to a preset abnormality handling strategy, which specifically includes: When the abnormal event is detected in the local RDMA operation indicator, the abnormal event is located to determine whether the abnormal location corresponding to the abnormal event can be detected. When the abnormal location is detected and the abnormal location matches a preset abnormality repair script, the abnormal location is repaired according to the abnormality repair script; When the abnormal location is not detected, or the detected abnormal location does not match the abnormal repair script, an abnormal alarm message is generated based on the abnormal event or the abnormal location and sent to the operation and maintenance platform.

[0007] As a preferred embodiment, the method further includes: Receive online status detection indication information sent by the master node; When this node is online, in response to the online status detection indication information, it sends a heartbeat message and local network card status information back to the master node; wherein, the heartbeat message is used to indicate that this node is online; the local network card status information is used to indicate whether the local network card is online or down. When the local network card is detected to be in a down state, a network card down state alarm message is sent to the operation and maintenance platform.

[0008] As a preferred embodiment, the method further includes: When this node comes back online or detects that the local network card has changed from a crashed state to an online state, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information; When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

[0009] As a preferred embodiment, the method further includes: When the current RDMA synchronization configuration information is received from the master node, the local RDMA configuration information is checked for missing configuration information based on the current RDMA synchronization configuration information. When it is detected that the current local RDMA configuration information has missing configuration information, the current local RDMA configuration information is supplemented with the current RDMA synchronization configuration information so that the supplemented local RDMA configuration information is consistent with the current RDMA synchronization configuration information, and the currently stored local RDMA synchronization configuration information is updated to the current RDMA synchronization configuration information. When it is detected that the missing configuration information does not exist in the current local RDMA configuration information, the RDMA synchronization configuration information stored locally is directly updated to the current RDMA synchronization configuration information.

[0010] A second aspect of the present invention provides an RDMA network configuration management device, comprising: The detection module is used to detect local RDMA configuration information and local RDMA operation indicators according to a preset detection cycle; wherein, the local RDMA configuration information is determined based on the RDMA synchronization configuration information issued by the master node in the same RDMA cluster; An exception handling module is used to handle exception events according to a preset exception handling strategy when an exception event is detected in the local RDMA configuration information or the local RDMA operation indicators.

[0011] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the RDMA network configuration management method according to any one of the first aspects.

[0012] A fourth aspect of the present invention provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the RDMA network configuration management method according to any one of the first aspects.

[0013] A fifth aspect of the present invention provides a computer program product, including a computer program / instructions, wherein when the computer program / instructions are executed by a processor, they implement the steps of the RDMA network configuration management method described in any of the first aspects.

[0014] Compared to existing technologies, the beneficial effects of this invention are that by having the master node be responsible for the unified distribution of RDMA synchronization configuration information within the same RDMA cluster, the consistency of RDMA network configuration among different nodes in the RDMA cluster can be guaranteed. Furthermore, by periodically detecting local RDMA configuration information and local RDMA operating indicators, and processing abnormal events according to a preset abnormality handling strategy when abnormal events are detected in local RDMA configuration information or local RDMA operating indicators, the timely detection and processing of abnormal RDMA network configuration or operating indicators of each node can be guaranteed, thereby ensuring the stable and efficient operation of the RDMA network. Attached Figure Description

[0015] Figure 1 This is a flowchart illustrating the RDMA network configuration management method in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the RDMA network configuration management device in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of the electronic device in an embodiment of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 The first aspect of this invention provides an RDMA network configuration management method, comprising the following steps S1 and S2: Step S1: According to the preset detection cycle, detect the local RDMA configuration information and local RDMA operation indicators; wherein, the local RDMA configuration information is determined based on the RDMA synchronization configuration information issued by the master node in the same RDMA cluster. Step S2: When an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicators, the abnormal event is processed according to the preset abnormal handling strategy.

[0018] Specifically, the RDMA cluster in this embodiment includes one master node and multiple slave nodes. The master and slave nodes are physical or virtual computing devices, each equipped with a network interface card (NIC) supporting RDMA functionality. Each slave node in this embodiment deploys an RDMA management process to execute the RDMA network configuration management method provided in this embodiment, uniformly managing the local RDMA configuration information and local RDMA operating metrics of that node. The master node is responsible for coordinating the management processes of all slave nodes. It configures RDMA synchronization configuration information and specifies various RDMA initialization operating metrics, and pushes them to all slave nodes in the same RDMA cluster. Since the master node is responsible for distributing RDMA synchronization configuration information, it does not run services to prevent service issues from affecting the RDMA management process.

[0019] To manage RDMA network configuration, this embodiment detects local RDMA configuration information and local RDMA operation metrics according to a preset detection period. It is understood that the detection period can be set according to the actual RDMA network configuration management needs, and this embodiment does not impose a specific limitation. For local RDMA configuration information, this embodiment determines whether there are any abnormal events by detecting whether there is configuration loss. For local RDMA operation metrics, this embodiment compares the RDMA initialization operation metrics issued by the master node during the initialization configuration phase with the current local RDMA operation metrics. If the difference between the current local RDMA operation metrics and the RDMA initialization operation metrics is greater than a preset difference threshold, it is determined that there is an abnormal event in the local RDMA operation metrics.

[0020] Furthermore, when abnormal events are detected in the local RDMA configuration information or local RDMA operation indicators, in order to avoid affecting the normal operation of the RDMA network, this embodiment processes the abnormal events in the local RDMA configuration information or local RDMA operation indicators according to the preset abnormal handling strategy. On the one hand, this can greatly reduce the cost of manual operation and maintenance, and on the other hand, it can ensure that the abnormal events in the local RDMA configuration information or local RDMA operation indicators are repaired in a timely manner, improve the efficiency of RDMA cluster operation and maintenance, and maintain the stable and efficient operation of the RDMA network.

[0021] The RDMA network configuration management method provided in this embodiment of the invention ensures the consistency of RDMA network configuration among different nodes in the RDMA cluster by having the master node be responsible for the unified distribution of RDMA synchronization configuration information within the same RDMA cluster. Furthermore, by periodically detecting local RDMA configuration information and local RDMA operation indicators, and handling abnormal events according to a preset abnormality handling strategy when abnormal events are detected in local RDMA configuration information or local RDMA operation indicators, the method ensures timely detection and handling of abnormal RDMA network configurations or operation indicators of each node, thereby guaranteeing the stable and efficient operation of the RDMA network.

[0022] As a preferred embodiment, when an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicators, the abnormal event is processed according to a preset abnormality handling strategy, specifically including: When an abnormal event is detected in the local RDMA configuration information, and the abnormal event is the loss of the local RDMA configuration information, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information. When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

[0023] Specifically, in this embodiment, when the loss of local RDMA configuration information is detected, an attempt is made to reload the local RDMA configuration information based on the currently stored local RDMA synchronization configuration information, and the number of loading failures is counted. It is understood that the preset loading failure threshold in this embodiment can be set according to actual application conditions. For example, if the preset loading failure threshold is 1 time, a local RDMA configuration failure alarm will be generated when the local RDMA configuration information cannot be loaded. Alternatively, if the preset loading failure threshold is 2, 3, 4, 5, etc., a local RDMA configuration failure alarm will be generated when the number of loading failures reaches the preset threshold. By sending the local RDMA configuration failure alarm to the operation and maintenance platform, operation and maintenance personnel can be notified in a timely manner to intervene and repair, reducing the impact of RDMA network fluctuations on service operation.

[0024] As a preferred embodiment, when an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicator, the abnormal event is processed according to a preset abnormality handling strategy, which specifically includes: When the abnormal event is detected in the local RDMA operation indicator, the abnormal event is located to determine whether the abnormal location corresponding to the abnormal event can be detected. When the abnormal location is detected and the abnormal location matches a preset abnormality repair script, the abnormal location is repaired according to the abnormality repair script; When the abnormal location is not detected, or the detected abnormal location does not match the abnormal repair script, an abnormal alarm message is generated based on the abnormal event or the abnormal location and sent to the operation and maintenance platform.

[0025] Specifically, this embodiment considers situations where the RDMA cluster network is complex, leading to complex RDMA network configuration. By detecting and repairing local RDMA operating indicators, it can adjust local RDMA operating indicators based on preset initialization RDMA operating indicators and real-time RDMA network status without manual intervention, ensuring the normal operation of the RDMA network. For example, during the initial configuration phase, the master node specifies a limit rate for the CRC (Cyclic Redundancy Check) error growth of the RDMA link. When the CRC error growth rate of the local RDMA link is detected to exceed this limit rate, it is determined that there is an abnormal event in this local RDMA operating indicator.

[0026] Furthermore, this embodiment pre-configures various anomaly repair scripts to address operational metric anomalies or errors that occur during RDMA operation. These scripts can be supplemented or updated promptly based on actual business scenarios. When an anomaly is detected in a local RDMA operational metric, anomaly analysis and localization are performed first, and an alarm is issued immediately. If the anomaly location is detected, indicating that the problem can be located, it is checked whether the location matches a pre-configured anomaly repair script. If they match, the anomaly location is repaired according to the repair strategy indicated in the script, thus achieving automated repair of the abnormal local RDMA operational metric without manual intervention. If they do not match or the repair of the anomaly location fails, an anomaly alarm is generated based on the current anomaly location and sent to the operations and maintenance platform to notify operations and maintenance personnel to intervene. If the anomaly location is not detected, an anomaly alarm is generated based on the current anomaly event and sent to the operations and maintenance platform. This anomaly event indicates the range of the anomaly location, helping operations and maintenance personnel quickly locate and handle the anomaly.

[0027] For example, suppose that when a decrease in RDMA flow rate is detected, the following steps are performed for anomaly location and repair: (1) First, check whether the network communication link of the local network card is unreachable and whether there is traffic on the physical network port; (2) Second, check whether the local network card is disabled or inactive; (3) Check whether the local network card's bond configuration is correct. All three steps can be detected through local anomaly location. If an anomaly is detected, the anomaly is repaired according to the matching anomaly repair script. If the anomaly cannot be detected based on the above three steps, the anomaly may involve the entire RDMA cluster or even the external environment. It is necessary to check whether the switch supports bond4 mode networking or check whether the networking meets the requirements. At this time, it is necessary to send an anomaly alarm message to notify the operation and maintenance personnel to intervene in the repair, thereby eliminating some possible anomaly locations, greatly saving the repair time of the operation and maintenance personnel, and ensuring the timely repair of RDMA network anomalies.

[0028] As a preferred embodiment, the method further includes: Receive online status detection indication information sent by the master node; When this node is online, in response to the online status detection indication information, it sends a heartbeat message and local network card status information back to the master node; wherein, the heartbeat message is used to indicate that this node is online; the local network card status information is used to indicate whether the local network card is online or down. When the local network card is detected to be in a down state, a network card down state alarm message is sent to the operation and maintenance platform.

[0029] Specifically, during the RDMA network configuration and management process, the master node periodically issues online status detection indication information to detect the online status of each slave node and ensure the normal operation of the RDMA network. Therefore, in this embodiment, when the slave node is online, it needs to respond to the online status detection indication information and send a heartbeat message to the master node. It is understood that if the slave node is offline, it will not send a heartbeat message to the master node. If the master node does not receive a heartbeat message from a slave node within a preset detection period, it determines that the slave node is abnormally offline and sends an alarm message to the operation and maintenance platform to notify the operation and maintenance personnel that the slave node is abnormally offline. The operation and maintenance personnel can then locate the specific cause of the offline and decide whether to intervene and repair it. Furthermore, in this embodiment, when the slave node is online, it also responds to the online status detection indication information to detect the operating status of the local network card and sends local network card status information back to the master node. This local network card status information is used to indicate whether the local network card is online or offline. Furthermore, when a local network card is detected to be down, a network card downtime alarm message is sent to the operation and maintenance platform, allowing the operation and maintenance personnel to locate the specific cause of the downtime and decide whether to intervene and repair it.

[0030] As a preferred embodiment, the method further includes: When this node comes back online or detects that the local network card has changed from a crashed state to an online state, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information; When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

[0031] Specifically, in this embodiment, when the local node comes back online or the local network card is detected to have returned from a downtime to an online state, in order to ensure that the local RDMA configuration is normal, it is necessary to reload the local RDMA configuration information based on the currently stored local RDMA synchronization configuration information, and then continue to execute the RDMA network configuration management process. If the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm message is generated and sent to the operation and maintenance platform to notify the operation and maintenance personnel to intervene and repair.

[0032] It is understood that the preset loading failure threshold in this embodiment can be set according to the actual application situation. For example, if the preset loading failure threshold is 1 time, a local RDMA configuration failure alarm message will be generated when the local RDMA configuration information cannot be loaded. Or if the preset loading failure threshold is 2, 3, 4, 5 times, etc., a local RDMA configuration failure alarm message will be generated when the number of loading failures of the local RDMA configuration information reaches the preset loading failure threshold.

[0033] As a preferred embodiment, the method further includes: When the current RDMA synchronization configuration information is received from the master node, the local RDMA configuration information is checked for missing configuration information based on the current RDMA synchronization configuration information. When it is detected that the current local RDMA configuration information has missing configuration information, the current local RDMA configuration information is supplemented with the current RDMA synchronization configuration information so that the supplemented local RDMA configuration information is consistent with the current RDMA synchronization configuration information, and the currently stored local RDMA synchronization configuration information is updated to the current RDMA synchronization configuration information. When it is detected that the missing configuration information does not exist in the current local RDMA configuration information, the RDMA synchronization configuration information stored locally is directly updated to the current RDMA synchronization configuration information.

[0034] Specifically, in this embodiment, the master node periodically synchronizes RDMA configuration information with each slave node in the same RDMA cluster. The synchronization time and frequency of the master node's RDMA configuration information can be set according to actual needs; this embodiment does not impose specific limitations on these settings. When receiving the current RDMA synchronization configuration information from the master node, this embodiment needs to check whether the current local RDMA configuration information is consistent with the current RDMA synchronization configuration information. If they are inconsistent, it indicates that the current local RDMA configuration information is incomplete and contains missing configuration information. Therefore, it is necessary to supplement the current local RDMA configuration information using the current RDMA synchronization configuration information to fill in the missing configuration information, ensuring that the supplemented local RDMA configuration information is consistent with the current RDMA synchronization configuration information, thereby guaranteeing the consistency of RDMA configuration information across all nodes in the same RDMA cluster. When it is detected that the current local RDMA configuration information does not contain any missing configuration information, indicating that the current local RDMA configuration information is complete, the currently stored RDMA synchronization configuration information is directly updated to the current RDMA synchronization configuration information.

[0035] Preferably, when supplementing the current local RDMA configuration information, if a configuration failure occurs, a configuration synchronization failure message is sent to the master node to instruct the master node to re-execute the configuration synchronization operation at a preset time interval, i.e., to re-issue the current RDMA synchronization configuration information. When the number of configuration synchronization failure messages received by the master node from the same slave node exceeds a preset threshold (e.g., the preset threshold is 2, 3, 4, etc., which is not specifically limited in this embodiment), the master node sends an alarm message to the operation and maintenance platform to notify the operation and maintenance personnel to intervene.

[0036] Please see Figure 2 A second aspect of the present invention provides an RDMA network configuration management device 100, comprising: The detection module 11 is used to detect local RDMA configuration information and local RDMA operation indicators according to a preset detection cycle; wherein, the local RDMA configuration information is determined based on the RDMA synchronization configuration information issued by the master node in the same RDMA cluster. The abnormal event handling module 12 is used to handle the abnormal event according to a preset abnormal event handling strategy when an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicator.

[0037] As a preferred embodiment, the abnormal event handling module 12 is used to handle the abnormal event according to a preset abnormal event handling strategy when an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicator, specifically including: When an abnormal event is detected in the local RDMA configuration information, and the abnormal event is the loss of the local RDMA configuration information, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information. When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

[0038] As a preferred embodiment, the abnormal event handling module 12 is used to handle the abnormal event according to a preset abnormal event handling strategy when an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicator, specifically including: When the abnormal event is detected in the local RDMA operation indicator, the abnormal event is located to determine whether the abnormal location corresponding to the abnormal event can be detected. When the abnormal location is detected and the abnormal location matches a preset abnormality repair script, the abnormal location is repaired according to the abnormality repair script; When the abnormal location is not detected, or the detected abnormal location does not match the abnormal repair script, an abnormal alarm message is generated based on the abnormal event or the abnormal location and sent to the operation and maintenance platform.

[0039] As a preferred embodiment, the device is further used for: Receive online status detection indication information sent by the master node; When this node is online, in response to the online status detection indication information, it sends a heartbeat message and local network card status information back to the master node; wherein, the heartbeat message is used to indicate that this node is online; the local network card status information is used to indicate whether the local network card is online or down. When the local network card is detected to be in a down state, a network card down state alarm message is sent to the operation and maintenance platform.

[0040] As a preferred embodiment, the device is further used for: When this node comes back online or detects that the local network card has changed from a crashed state to an online state, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information; When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

[0041] As a preferred embodiment, the device is further used for: When the current RDMA synchronization configuration information is received from the master node, the local RDMA configuration information is checked for missing configuration information based on the current RDMA synchronization configuration information. When it is detected that the current local RDMA configuration information has missing configuration information, the current local RDMA configuration information is supplemented with the current RDMA synchronization configuration information so that the supplemented local RDMA configuration information is consistent with the current RDMA synchronization configuration information, and the currently stored local RDMA synchronization configuration information is updated to the current RDMA synchronization configuration information. When it is detected that the missing configuration information does not exist in the current local RDMA configuration information, the RDMA synchronization configuration information stored locally is directly updated to the current RDMA synchronization configuration information.

[0042] The RDMA network configuration management device 100 provided in this embodiment of the invention ensures the consistency of RDMA network configuration among different nodes in the RDMA cluster by having the master node be responsible for the unified distribution of RDMA synchronization configuration information within the same RDMA cluster. Furthermore, by periodically detecting local RDMA configuration information and local RDMA operation indicators, and processing abnormal events according to a preset abnormality handling strategy when abnormal events are detected in local RDMA configuration information or local RDMA operation indicators, the device ensures timely detection and processing of abnormal RDMA network configuration or operation indicators of each node, thereby ensuring the stable and efficient operation of the RDMA network.

[0043] Please see Figure 3 The third aspect of the present invention provides an electronic device 200, including a memory 22, a processor 21, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, it implements the RDMA network configuration management method described in any embodiment of the first aspect.

[0044] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device 200.

[0045] The electronic device 200 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 200 and does not constitute a limitation on the electronic device 200. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the electronic device 200 may also include input / output devices, network access devices, buses, etc.

[0046] The processor 21 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor 21 can be any conventional processor 21. The processor 21 is the control center of the electronic device 200, connecting various parts of the electronic device 200 via various interfaces and lines.

[0047] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the electronic device 200 by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0048] A fourth aspect of the present invention provides a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the RDMA network configuration management method described in any embodiment of the first aspect.

[0049] A fifth aspect of the present invention provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the RDMA network configuration management method described in any embodiment of the first aspect.

[0050] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0051] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for configuring and managing RDMA networks, characterized in that, include: According to the preset detection cycle, the local RDMA configuration information and local RDMA operation indicators are detected; wherein, the local RDMA configuration information is determined based on the RDMA synchronization configuration information issued by the master node in the same RDMA cluster. When an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicators, the abnormal event is handled according to a preset abnormality handling strategy.

2. The RDMA network configuration management method as described in claim 1, characterized in that, When an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicators, the abnormal event is handled according to a preset abnormality handling strategy, specifically including: When an abnormal event is detected in the local RDMA configuration information, and the abnormal event is the loss of the local RDMA configuration information, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information. When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

3. The RDMA network configuration management method as described in claim 1, characterized in that, When an abnormal event is detected in the local RDMA configuration information or the local RDMA operation indicators, the abnormal event is handled according to a preset abnormality handling strategy, specifically including: When the abnormal event is detected in the local RDMA operation indicator, the abnormal event is located to determine whether the abnormal location corresponding to the abnormal event can be detected. When the abnormal location is detected and the abnormal location matches a preset abnormality repair script, the abnormal location is repaired according to the abnormality repair script; When the abnormal location is not detected, or the detected abnormal location does not match the abnormal repair script, an abnormal alarm message is generated based on the abnormal event or the abnormal location and sent to the operation and maintenance platform.

4. The RDMA network configuration management method as described in claim 1, characterized in that, The method further includes: Receive online status detection indication information sent by the master node; When this node is online, in response to the online status detection indication information, it sends a heartbeat message and local network card status information back to the master node; wherein, the heartbeat message is used to indicate that this node is online; the local network card status information is used to indicate whether the local network card is online or down. When the local network card is detected to be in a down state, a network card down state alarm message is sent to the operation and maintenance platform.

5. The RDMA network configuration management method as described in claim 4, characterized in that, The method further includes: When this node comes back online or detects that the local network card has changed from a crashed state to an online state, the local RDMA configuration information is reloaded based on the currently stored local RDMA synchronization configuration information; When the number of failed loading attempts of the local RDMA configuration information reaches a preset failure threshold, a local RDMA configuration failure alarm is generated and sent to the operation and maintenance platform.

6. The RDMA network configuration management method as described in claim 1, characterized in that, The method further includes: When the current RDMA synchronization configuration information is received from the master node, the local RDMA configuration information is checked for missing configuration information based on the current RDMA synchronization configuration information. When it is detected that the current local RDMA configuration information has missing configuration information, the current local RDMA configuration information is supplemented with the current RDMA synchronization configuration information so that the supplemented local RDMA configuration information is consistent with the current RDMA synchronization configuration information, and the currently stored local RDMA synchronization configuration information is updated to the current RDMA synchronization configuration information. When it is detected that the missing configuration information does not exist in the current local RDMA configuration information, the RDMA synchronization configuration information stored locally is directly updated to the current RDMA synchronization configuration information.

7. An RDMA network configuration management device, characterized in that, include: The detection module is used to detect local RDMA configuration information and local RDMA operation indicators according to a preset detection cycle; wherein, the local RDMA configuration information is determined based on the RDMA synchronization configuration information issued by the master node in the same RDMA cluster; An exception handling module is used to handle exception events according to a preset exception handling strategy when an exception event is detected in the local RDMA configuration information or the local RDMA operation indicators.

8. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the RDMA network configuration management method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the RDMA network configuration management method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program / instruction that, when executed by a processor, implements the steps of the RDMA network configuration management method according to any one of claims 1 to 6.

Images