CN109379130B - Network reconstruction method based on fiber channel node card - Google Patents
Network reconstruction method based on fiber channel node card Download PDFInfo
- Publication number
- CN109379130B CN109379130B CN201811389607.8A CN201811389607A CN109379130B CN 109379130 B CN109379130 B CN 109379130B CN 201811389607 A CN201811389607 A CN 201811389607A CN 109379130 B CN109379130 B CN 109379130B
- Authority
- CN
- China
- Prior art keywords
- node
- nrt
- network
- reconstruction
- nodes
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/03—Arrangements for fault recovery
- H04B10/032—Arrangements for fault recovery using working and protection systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/077—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using a supervisory or additional signal
Abstract
The invention provides a network reconstruction method based on a fiber channel node card, wherein fault detection is responsible for collecting health state information of each node, including life messages and self-period self-checking results, a reconstruction decision is responsible for executing the whole reconstruction process, including stopping system operation, reloading node configuration files, reloading application programs and restarting the system, if any node is in a fault state and a backup node is in a normal state after the system acquires the health state of each node through the life messages. The network reconstruction method based on the fiber channel node card adopts the strategy of N +1 backup, solves the problem of whole function loss caused by single node failure in the fiber channel network, has the advantages of short reconstruction time and simple realization, and can effectively improve the reliability of the system.
Description
Technical Field
The invention relates to the technical field of airborne buses, in particular to a network reconstruction method for a fiber channel node card.
Background
With the development of the technology, the high-speed fibre channel bus is already mature and applied to military aircraft, and all the equipment on the aircraft are interconnected through the high-speed fibre channel bus.
When the airborne high-speed fiber channel network fails, the airborne equipment cannot normally operate, in order to improve the reliability of an airborne system, when a network node in the system fails, a backup node can take over the failed node to continue working, and the process is called network reconstruction. The network reconfiguration relates to the configuration switching of a fiber channel network, fault detection, reconfiguration decision and the like of each network node. By the method of network reconstruction, the system does not lose the whole function due to the single node failure in the network, and the method is an effective method for improving the reliability of the system.
At present, the problems of overlong network reconstruction of an optical fiber channel in the airborne field, system reliability reduction caused by repeated reconstruction and the like exist. The reconstruction time can be reduced by optimizing the fault detection process, limiting the reconstruction times and other measures, the influence of the reconstruction process on the system is reduced, and the reliability of the system is improved.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a network reconstruction method based on a fiber channel node card, when a certain node in a network fails, a backup node can take over the failed node to continue to operate, so that the overall function of the system is not influenced.
The technical scheme adopted by the invention for solving the technical problem comprises the following steps:
step 1: system initialization
An optical fiber network system comprises a switch and N network nodes, wherein the network nodes are divided into 2 types, namely network controller nodes (Net Control, NC) and network Remote Terminal nodes (Net Remote Terminal, NRT), when the optical fiber network system is started, each node loads an initial configuration scheme by default, and the initial configuration scheme refers to that when an optical fiber channel carries out networking communication, each network node needs to configure information such as a port address, a port role, a source address and a destination address of a sent message, a source address of a received message and the like and a message ID;
when the configuration scheme is designed, messages are divided into two types of life messages and application messages:
(1) the life message is used for transmitting network reconstruction related information, namely, the network controller node performs fault detection on each NRT node through the life message, and the network controller node sends a reconstruction command or acquires a reconstruction completion state through the life message;
(2) the application message refers to application information transmitted by each node in the optical fiber network to complete certain functions, and specific application messages are defined according to application scenes used by the network;
in an optical fiber network system composed of N nodes, a node 1 is set as a network controller node, nodes 2 to N are set as network remote terminal nodes, wherein the node 2 is set as a backup node, and nodes 3 to N are set as nodes which normally work, in a system initialization state, all nodes load a scheme 1, and configuration information of the scheme 1 is as follows:
(1) all nodes have no fault, and the node 2 is in a backup state;
(2) the network controller node 1 interacts life messages with all other nodes;
(3) the backup node 2 only carries out life message interaction with the network controller node 1;
(4) the nodes 3 to N which work normally have application message interaction with each other;
other schemes are schemes which need to be loaded during reconstruction, when any one of the nodes 3 to the node N has a fault and corresponds to a configuration scheme, a backup node in the configuration scheme takes over the work of the fault node, the message of the whole system needs to be remapped and configured, and the configuration information of the configuration scheme is as follows:
(1) if the node M (2< M < N +1) fails, the node 2 takes over the node M to work;
(2) the network controller node 1 interacts life messages with all other nodes except the node M;
(3) the backup node 2 uses the application message configuration of the node M to change the source address of the sent message into the port address of the node 2;
(4) the node M does not interact with any node for life messages and application messages;
(5) a node having application message interaction with the node M changes the source address of part of received messages into the port address of the node 2;
all configuration information is shown in table 1:
TABLE 1 System configuration scheme Table
Step 2: fault detection
In the initial state, the network controller node 1 receives the life messages of each NRT node, determines the "health state" of the current NRT node according to the "heartbeat count" field and the "health state" field in the life messages, and the specific determination process is as follows:
a) in the initial state, setting the 'health state' fields of all NRT nodes to be 'healthy';
b) when the NRT node sends a life message each time, the heartbeat counting field starts from 0 and is added with 1 each time;
c) when a network controller node receives a life message of a certain NRT node, recording the value of a heartbeat counting field of the current NRT node;
d) when the network controller node receives the life message of the NRT node next time, comparing the heartbeat count recorded last time with the heartbeat count field in the life message, if the heartbeat count recorded last time plus 1 is equal to the heartbeat count in the life message, determining that the health state of the NRT node is normal, and recording the heartbeat count in the life message;
if the heartbeat count of the last time is not equal to the heartbeat count in the current life message plus 1, the NRT node is considered to be in fault, in order to reduce the false alarm rate, if the heartbeat count of the last time is continuously increased for 3 times and 1 is not equal to the heartbeat count in the current life message, the health state of the NRT node is considered to be in fault, and if the condition that the heartbeat count of the last time is increased by 1 and is not equal to the heartbeat count in the current life message does not meet the condition that the condition is continuously increased for 3 times, the health state of the NRT node is considered to be in normal;
e) the network controller node reports the health state of each NRT node to a reconstruction decision part, and repeats the step b) to the step until the system stops running;
and step 3: reconstruction decisions
After receiving the health state of each node, the reconstruction decision part of the network controller node performs reconstruction decisions, and the specific reconstruction decisions are divided into the following 3 conditions:
(1) when any NRT node between the node 3 and the node N has a fault, the current backup node has no fault, and reconstruction does not occur before, the network controller node determines system reconstruction and sends a reconstruction command to each NRT node, the whole system can select a corresponding reconstruction scheme according to the reconstruction scheme shown in the table 1 and reload, and the NRT node with the fault does not receive and send any message any more;
(2) when any NRT node between the node 3 and the node N has a fault and the current backup node also has a fault, the network controller node decides not to reconstruct and the system maintains the current state to continue to operate;
(3) if the system is reconstructed once, when any NRT node between the node 3 and the node N fails, the network controller node decides not to reconstruct and the system maintains the current state to continue to operate;
and 4, step 4: system reconfiguration execution
a) When the network controller decides to reconstruct, sending a reconstruction command to all NRT nodes;
b) after each NRT node receives a reconfiguration command sent by a network controller, suspending a task of an application program, and not processing the application program because a backup node does not run the application program, wherein the reconfiguration command contains a new configuration scheme number;
c) reinitializing the fibre channel bus, reloading the configuration scheme according to the configuration scheme number sent by the network controller,
d) the network continues to be initialized so that the fibre channel daughter card is ready to send and receive messages.
e) And reloading the application program, wherein for the backup node, the application program of the previous failed node needs to be reloaded. For other common nodes, the application program of the node needs to be reloaded and the node is ready to be reported to the NC, and the system can be restarted and waits for the NC to send a start operation command.
f) And after receiving the readiness of all the NRT nodes, the NC starts to send a running starting command to the whole network. After each NRT node receives the operation starting command, each application program is operated, and the network starts to work normally.
The network reconstruction method based on the fiber channel node card has the advantages that the network reconstruction method based on the fiber channel node card adopts an N +1 backup strategy, solves the problem of whole function loss caused by single node failure in a fiber channel network, has short reconstruction time and simple realization, and can effectively improve the reliability of a system.
Drawings
FIG. 1 is a diagram illustrating a node card reloading configuration information according to the present invention.
FIG. 2 is a schematic diagram of the system of the present invention in normal operation.
FIG. 3 is a schematic representation of the system of the present invention as it operates upon reconstruction.
Fig. 4 is a flow chart of the system fault detection of the present invention.
FIG. 5 is a flow chart of the system reconfiguration of the present invention.
Detailed Description
The invention is further illustrated with reference to the following figures and examples.
In order to achieve the above purpose, the method of the present invention includes three parts of fault detection, reconstruction decision and reconstruction execution, as shown in fig. 1-3.
Further, fault detection is mainly responsible for collecting health state information of each node, including life messages and self-periodic self-checking results.
Furthermore, the reconfiguration decision is mainly responsible for that after the system acquires the health state of each node through the life message, if any node is in a fault state and the backup node is in a normal state, the system needs to be reconfigured.
Furthermore, the reconfiguration execution is mainly responsible for executing the whole reconfiguration process, including stopping system operation, reloading the node configuration file, reloading the application program, and restarting the system.
Step 1: system initialization
An optical fiber network system comprises a switch and N network nodes, wherein the network nodes are divided into 2 types, namely network controller nodes (Net Control, NC) and network Remote Terminal nodes (Net Remote Terminal, NRT), when the optical fiber network system is started, each node loads an initial configuration scheme by default, and the initial configuration scheme refers to that each network node needs to configure information such as a port address, a port role, a source address and a destination address of a sent message, a source address of a received message and the like and a message ID when an optical fiber channel carries out networking communication.
When the configuration scheme is designed, messages are divided into two types of life messages and application messages:
(1) the life message is used for transmitting information related to network reconstruction, namely, the network controller node performs fault detection on each NRT node through the life message, and the network controller node sends a reconstruction command or acquires a reconstruction completion state through the life message.
(2) The application message refers to application information transmitted by each node in the optical fiber network to complete certain functions, and specific application messages are defined according to application scenes used by the network, for example, in the airborne field, the application messages can transmit airplane attitude information, fire control information, target information and the like.
In an optical fiber network system composed of N nodes, a node 1 is set as a network controller node, nodes 2 to N are set as network remote terminal nodes, wherein the node 2 is set as a backup node, and nodes 3 to N are set as nodes which normally work, in a system initialization state, all nodes load a scheme 1, and configuration information of the scheme 1 is as follows:
(1) all nodes have no fault, and the node 2 is in a backup state;
(2) the network controller node 1 interacts life messages with all other nodes;
(3) the backup node 2 only carries out life message interaction with the network controller node 1;
(4) the nodes 3 to N which work normally have application message interaction with each other;
other schemes are schemes which need to be loaded during reconstruction, when any one of the nodes 3 to the node N has a fault and corresponds to a configuration scheme, a backup node in the configuration scheme takes over the work of the fault node, the message of the whole system needs to be remapped and configured, and the configuration information of the configuration scheme is as follows:
(1) if the node M (2< M < N +1) fails, the node 2 takes over the node M to work;
(2) the network controller node 1 interacts life messages with all other nodes except the node M;
(3) the backup node 2 uses the application message configuration of the node M to change the source address of the sent message into the port address of the node 2;
(4) the node M does not interact with any node for life messages and application messages;
(5) a node having application message interaction with the node M changes the source address of part of received messages into the port address of the node 2;
all configuration information is shown in table 1:
TABLE 1 System configuration scheme Table
Step 2: fault detection
In the initial state, the network controller node 1 receives the life messages of each NRT node, determines the "health state" of the current NRT node according to the "heartbeat count" field and the "health state" field in the life messages, and the flow of fault detection is shown in fig. 4, where the specific determination flow is:
a) in the initial state, setting the 'health state' fields of all NRT nodes to be 'healthy';
b) when the NRT node sends a life message each time, the heartbeat counting field starts from 0 and is added with 1 each time;
c) when a network controller node receives a life message of a certain NRT node, recording the value of a heartbeat counting field of the current NRT node;
d) when the network controller node receives the life message of the NRT node next time, comparing the heartbeat count recorded last time with the heartbeat count field in the life message, if the heartbeat count recorded last time plus 1 is equal to the heartbeat count in the life message, determining that the health state of the NRT node is normal, and recording the heartbeat count in the life message;
if the heartbeat count of the last time is not equal to the heartbeat count in the current life message plus 1, the NRT node is considered to be in fault, in order to reduce the false alarm rate, if the heartbeat count of the last time is continuously increased for 3 times and 1 is not equal to the heartbeat count in the current life message, the health state of the NRT node is considered to be in fault, and if the condition that the heartbeat count of the last time is increased by 1 and is not equal to the heartbeat count in the current life message does not meet the condition that the condition is continuously increased for 3 times, the health state of the NRT node is considered to be in normal;
e) the network controller node reports the health state of each NRT node to a reconstruction decision part, and repeats the step b) to the step until the system stops running;
and step 3: reconstruction decisions
After receiving the health state of each node, the reconstruction decision part of the network controller node performs reconstruction decisions, and the specific reconstruction decisions are divided into the following 3 conditions:
(1) when any NRT node between the node 3 and the node N has a fault, the current backup node has no fault, and reconstruction does not occur before, the network controller node determines system reconstruction and sends a reconstruction command to each NRT node, the whole system can select a corresponding reconstruction scheme according to the reconstruction scheme shown in the table 1 and reload, and the NRT node with the fault does not receive and send any message any more;
(2) when any NRT node between the node 3 and the node N has a fault and the current backup node also has a fault, the network controller node decides not to reconstruct and the system maintains the current state to continue to operate;
(3) if the system is reconstructed once, when any NRT node between the node 3 and the node N fails, the network controller node decides not to reconstruct and the system maintains the current state to continue to operate;
and 4, step 4: system reconfiguration execution
a) When the network controller decides to reconstruct, sending a reconstruction command to all NRT nodes;
b) after each NRT node receives a reconfiguration command sent by a network controller, suspending a task of an application program, and not processing the application program because a backup node does not run the application program, wherein the reconfiguration command contains a new configuration scheme number;
c) reinitializing the fibre channel bus, reloading the configuration scheme according to the configuration scheme number sent by the network controller,
d) the network continues to be initialized so that the fibre channel daughter card is ready to send and receive messages.
e) And reloading the application program, wherein for the backup node, the application program of the previous failed node needs to be reloaded. For other common nodes, the application program of the node needs to be reloaded and the node is ready to be reported to the NC, and the system can be restarted and waits for the NC to send a start operation command.
f) And after receiving the readiness of all the NRT nodes, the NC starts to send a running starting command to the whole network. After each NRT node receives the operation starting command, each application program is operated, and the network starts to work normally.
A flow chart of the entire process is shown in fig. 5.
Claims (1)
1. A network reconstruction method based on a fiber channel node card is characterized by comprising the following steps:
step 1: system initialization
An optical fiber network system comprises a switch and N network nodes, wherein the network nodes are divided into 2 types, namely network controller nodes (Net Control, NC) and network Remote Terminal nodes (Net Remote Terminal, NRT), when the optical fiber network system is started, each node loads an initial configuration scheme by default, and the initial configuration scheme refers to that when an optical fiber channel carries out networking communication, each network node needs to configure information such as a port address, a port role, a source address and a destination address of a sent message, a source address of a received message and the like and a message ID;
when the configuration scheme is designed, messages are divided into two types of life messages and application messages:
(1) the life message is used for transmitting network reconstruction related information, namely, the network controller node performs fault detection on each NRT node through the life message, and the network controller node sends a reconstruction command or acquires a reconstruction completion state through the life message;
(2) the application message refers to application information transmitted by each node in the optical fiber network to complete certain functions, and specific application messages are defined according to application scenes used by the network;
in an optical fiber network system composed of N nodes, a node 1 is set as a network controller node, nodes 2 to N are set as network remote terminal nodes, wherein the node 2 is set as a backup node, and nodes 3 to N are set as nodes which normally work, in a system initialization state, all nodes load a scheme 1, and configuration information of the scheme 1 is as follows:
(1) all nodes have no fault, and the node 2 is in a backup state;
(2) the network controller node 1 interacts life messages with all other nodes;
(3) the backup node 2 only carries out life message interaction with the network controller node 1;
(4) the nodes 3 to N which work normally have application message interaction with each other;
other schemes are schemes which need to be loaded during reconstruction, when any one of the nodes 3 to the node N has a fault and corresponds to a configuration scheme, a backup node in the configuration scheme takes over the work of the fault node, the message of the whole system needs to be remapped and configured, and the configuration information of the configuration scheme is as follows:
(1) if the node M fails, 2< M < N +1, and the node 2 takes over the node M to work;
(2) the network controller node 1 interacts life messages with all other nodes except the node M;
(3) the backup node 2 uses the application message configuration of the node M to change the source address of the sent message into the port address of the node 2;
(4) the node M does not interact with any node for life messages and application messages;
(5) a node having application message interaction with the node M changes the source address of part of received messages into the port address of the node 2;
all configuration information is shown in table 1:
TABLE 1 System configuration scheme Table
Step 2: fault detection
In the initial state, the network controller node 1 receives the life messages of each NRT node, determines the "health state" of the current NRT node according to the "heartbeat count" field and the "health state" field in the life messages, and the specific determination process is as follows:
a) in the initial state, setting the 'health state' fields of all NRT nodes to be 'healthy';
b) when the NRT node sends a life message each time, the heartbeat counting field starts from 0 and is added with 1 each time;
c) when a network controller node receives a life message of a certain NRT node, recording the value of a heartbeat counting field of the current NRT node;
d) when the network controller node receives the life message of the NRT node next time, comparing the heartbeat count recorded last time with the heartbeat count field in the life message, if the heartbeat count recorded last time plus 1 is equal to the heartbeat count in the life message, determining that the health state of the NRT node is normal, and recording the heartbeat count in the life message;
if the heartbeat count of the last record plus 1 is not equal to the heartbeat count in the current life message, the NRT node is considered to be in fault, and if the heartbeat count of the last record plus 1 is not equal to the heartbeat count in the current life message for continuously 3 times in order to reduce the false alarm rate, the health state of the NRT node is considered to be in fault;
e) the network controller node reports the health state of each NRT node to a reconstruction decision part, and repeats the step b) to the step until the system stops running;
and step 3: reconstruction decisions
After receiving the health state of each node, the reconstruction decision part of the network controller node performs reconstruction decisions, and the specific reconstruction decisions are divided into the following 3 conditions:
(1) when any NRT node between the node 3 and the node N has a fault, the current backup node has no fault, and reconstruction does not occur before, the network controller node determines system reconstruction and sends a reconstruction command to each NRT node, the whole system can select a corresponding reconstruction scheme according to the reconstruction scheme shown in the table 1 and reload, and the NRT node with the fault does not receive and send any message any more;
(2) when any NRT node between the node 3 and the node N has a fault and the current backup node also has a fault, the network controller node decides not to reconstruct and the system maintains the current state to continue to operate;
(3) if the system is reconstructed once, when any NRT node between the node 3 and the node N fails, the network controller node decides not to reconstruct and the system maintains the current state to continue to operate;
and 4, step 4: system reconfiguration execution
a) When the network controller decides to reconstruct, sending a reconstruction command to all NRT nodes;
b) after each NRT node receives a reconfiguration command sent by a network controller, suspending a task of an application program, and not processing the application program because a backup node does not run the application program, wherein the reconfiguration command contains a new configuration scheme number;
c) reinitializing the fibre channel bus, reloading the configuration scheme according to the configuration scheme number sent by the network controller,
d) continuing to initialize the network to make the sub-fiber channel card ready to receive and transmit messages;
e) reloading the application program, wherein for the backup node, the application program of the previous fault node needs to be reloaded, for other common nodes, the application program of the node needs to be reloaded, the node reports the readiness to the NC, the system can be restarted, and the NC is waited to send a running start command;
f) and after receiving the ready state of all the NRT nodes, the NC starts to send an operation starting command to the whole network, and after receiving the operation starting command, each NRT node runs each application program, so that the network starts to work normally.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811389607.8A CN109379130B (en) | 2018-11-21 | 2018-11-21 | Network reconstruction method based on fiber channel node card |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811389607.8A CN109379130B (en) | 2018-11-21 | 2018-11-21 | Network reconstruction method based on fiber channel node card |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109379130A CN109379130A (en) | 2019-02-22 |
CN109379130B true CN109379130B (en) | 2021-09-10 |
Family
ID=65376930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811389607.8A Active CN109379130B (en) | 2018-11-21 | 2018-11-21 | Network reconstruction method based on fiber channel node card |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109379130B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110166856B (en) * | 2019-05-09 | 2021-07-16 | 中国航空工业集团公司西安航空计算技术研究所 | Fiber channel network reconstruction design method and device |
CN113708830B (en) * | 2021-09-06 | 2023-11-14 | 天津津航计算技术研究所 | Comprehensive avionics system backup method based on optical fiber network |
CN113541775B (en) * | 2021-09-15 | 2022-01-28 | 北京国科天迅科技有限公司 | Optical fiber bus fault reconstruction system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105471692A (en) * | 2014-07-29 | 2016-04-06 | 华为技术有限公司 | Network intercommunication method and network intercommunication equipment |
CN106462544A (en) * | 2014-03-31 | 2017-02-22 | 亚马逊科技公司 | Session management in distributed storage systems |
CN108228097A (en) * | 2017-12-25 | 2018-06-29 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of power-off protection method based on FAT32 file system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8759380B2 (en) * | 2011-04-22 | 2014-06-24 | Cytokinetics, Inc. | Certain heterocycles, compositions thereof, and methods for their use |
US9155098B2 (en) * | 2012-03-29 | 2015-10-06 | Qualcomm Incorporated | Channel state information reference signal (CSI-RS) configuration and CSI reporting restrictions |
-
2018
- 2018-11-21 CN CN201811389607.8A patent/CN109379130B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106462544A (en) * | 2014-03-31 | 2017-02-22 | 亚马逊科技公司 | Session management in distributed storage systems |
CN105471692A (en) * | 2014-07-29 | 2016-04-06 | 华为技术有限公司 | Network intercommunication method and network intercommunication equipment |
CN108228097A (en) * | 2017-12-25 | 2018-06-29 | 中国航空工业集团公司洛阳电光设备研究所 | A kind of power-off protection method based on FAT32 file system |
Non-Patent Citations (1)
Title |
---|
基于MPC8308的光纤旁路保护器系统设计与实现;伍召学;《电视技术》;20140402;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN109379130A (en) | 2019-02-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109379130B (en) | Network reconstruction method based on fiber channel node card | |
US20040153844A1 (en) | Failure analysis method and system for storage area networks | |
CN109286529B (en) | Method and system for recovering RabbitMQ network partition | |
US20140149985A1 (en) | Control method for i/o device and virtual computer system | |
US10348616B2 (en) | Packet transmission method and apparatus, and interconnect interface | |
WO2015169199A1 (en) | Anomaly recovery method for virtual machine in distributed environment | |
CN109803024B (en) | Method for cluster node network | |
CN102882704B (en) | Link protection method in the soft reboot escalation process of a kind of ISSU and equipment | |
CN108429629A (en) | Equipment fault restoration methods and device | |
CN106960060B (en) | Database cluster management method and device | |
CN109698775A (en) | A kind of dual-machine redundancy backup system based on real-time status detection | |
CN109391691B (en) | Method and related device for recovering NAS service under single-node fault | |
CN106874142B (en) | Real-time data fault-tolerant processing method and system | |
CN103905247A (en) | Two-unit standby method and system based on multi-client judgment | |
CN113656175A (en) | Method, apparatus and program product for training models based on distributed systems | |
CN112527567A (en) | System disaster tolerance method, device, equipment and storage medium | |
CN107948063B (en) | Method for establishing aggregation link and access equipment | |
CN110427283B (en) | Dual-redundancy fuel management computer system | |
CN116699964A (en) | Redundant operation method and system for industrial process controller | |
US20060053330A1 (en) | Smart card for high-availability clustering | |
CN111399766A (en) | Data storage method, data reading method, device and system in storage system | |
CN105068763B (en) | A kind of virtual machine tolerant system and method for storage failure | |
CN101557307B (en) | Dispatch automation system application state management method | |
US20150195167A1 (en) | Availability device, storage area network system with availability device and methods for operation thereof | |
CN116027705A (en) | Main-standby switching and data synchronizing system and method for programmable controller |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |